From db5914695a84a7b128ec2e4e9272e6e8091753e1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Jan 2024 11:25:57 +0000 Subject: inet_diag: add module pointer to "struct inet_diag_handler" Following patch is going to use RCU instead of inet_diag_table_mutex acquisition. This patch is a preparation, no change of behavior yet. Signed-off-by: Eric Dumazet Reviewed-by: Guillaume Nault Reviewed-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/inet_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 84abb30a3fbb..a9033696b0aa 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -8,6 +8,7 @@ struct inet_hashinfo; struct inet_diag_handler { + struct module *owner; void (*dump)(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r); -- cgit v1.2.3 From 114b4bb1cc19239b272d52ebbe156053483fe2f8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Jan 2024 11:25:59 +0000 Subject: sock_diag: add module pointer to "struct sock_diag_handler" Following patch is going to use RCU instead of sock_diag_table_mutex acquisition. This patch is a preparation, no change of behavior yet. Signed-off-by: Eric Dumazet Reviewed-by: Guillaume Nault Reviewed-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/sock_diag.h | 1 + net/ipv4/inet_diag.c | 2 ++ net/netlink/diag.c | 1 + net/packet/diag.c | 1 + net/smc/smc_diag.c | 1 + net/tipc/diag.c | 1 + net/unix/diag.c | 1 + net/vmw_vsock/diag.c | 1 + net/xdp/xsk_diag.c | 1 + 9 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 0b9ecd8cf979..7c07754d711b 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -13,6 +13,7 @@ struct nlmsghdr; struct sock; struct sock_diag_handler { + struct module *owner; __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index abf7dc982796..52ce20691e4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1488,6 +1488,7 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } static const struct sock_diag_handler inet_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1495,6 +1496,7 @@ static const struct sock_diag_handler inet_diag_handler = { }; static const struct sock_diag_handler inet6_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET6, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 1eeff9422856..e12c90d5f6ad 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -241,6 +241,7 @@ static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler netlink_diag_handler = { + .owner = THIS_MODULE, .family = AF_NETLINK, .dump = netlink_diag_handler_dump, }; diff --git a/net/packet/diag.c b/net/packet/diag.c index 9a7980e3309d..b3bd2f6c2bf7 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -245,6 +245,7 @@ static int packet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler packet_diag_handler = { + .owner = THIS_MODULE, .family = AF_PACKET, .dump = packet_diag_handler_dump, }; diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 52f7c4f1e767..32bad267fa3e 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -255,6 +255,7 @@ static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler smc_diag_handler = { + .owner = THIS_MODULE, .family = AF_SMC, .dump = smc_diag_handler_dump, }; diff --git a/net/tipc/diag.c b/net/tipc/diag.c index 18733451c9e0..54dde8c4e4d4 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -95,6 +95,7 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, } static const struct sock_diag_handler tipc_sock_diag_handler = { + .owner = THIS_MODULE, .family = AF_TIPC, .dump = tipc_sock_diag_handler_dump, }; diff --git a/net/unix/diag.c b/net/unix/diag.c index bec09a3a1d44..c3648b706509 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -322,6 +322,7 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler unix_diag_handler = { + .owner = THIS_MODULE, .family = AF_UNIX, .dump = unix_diag_handler_dump, }; diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c index 2e29994f92ff..ab87ef66c1e8 100644 --- a/net/vmw_vsock/diag.c +++ b/net/vmw_vsock/diag.c @@ -157,6 +157,7 @@ static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler vsock_diag_handler = { + .owner = THIS_MODULE, .family = AF_VSOCK, .dump = vsock_diag_handler_dump, }; diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 9f8955367275..09dcea0cbbed 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -194,6 +194,7 @@ static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) } static const struct sock_diag_handler xsk_diag_handler = { + .owner = THIS_MODULE, .family = AF_XDP, .dump = xsk_diag_handler_dump, }; -- cgit v1.2.3 From 86e8921df05c6e9423ab74ab8d41022775d8b83a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Jan 2024 11:26:01 +0000 Subject: sock_diag: allow concurrent operation in sock_diag_rcv_msg() TCPDIAG_GETSOCK and DCCPDIAG_GETSOCK diag are serialized on sock_diag_table_mutex. This is to make sure inet_diag module is not unloaded while diag was ongoing. It is time to get rid of this mutex and use RCU protection, allowing full parallelism. Signed-off-by: Eric Dumazet Reviewed-by: Guillaume Nault Reviewed-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/sock_diag.h | 9 +++++++-- net/core/sock_diag.c | 43 ++++++++++++++++++++++++++----------------- net/ipv4/inet_diag.c | 9 +++++++-- 3 files changed, 40 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 7c07754d711b..110978dc9af1 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -23,8 +23,13 @@ struct sock_diag_handler { int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); -void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); -void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); +struct sock_diag_inet_compat { + struct module *owner; + int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh); +}; + +void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr); +void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr); u64 __sock_gen_cookie(struct sock *sk); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 72009e1f4380..5c3666431df4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -17,8 +17,9 @@ #include static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX]; -static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); -static DEFINE_MUTEX(sock_diag_table_mutex); + +static struct sock_diag_inet_compat __rcu *inet_rcv_compat; + static struct workqueue_struct *broadcast_wq; DEFINE_COOKIE(sock_cookie); @@ -184,19 +185,20 @@ void sock_diag_broadcast_destroy(struct sock *sk) queue_work(broadcast_wq, &bsk->work); } -void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr) { - mutex_lock(&sock_diag_table_mutex); - inet_rcv_compat = fn; - mutex_unlock(&sock_diag_table_mutex); + xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, + ptr); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); -void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr) { - mutex_lock(&sock_diag_table_mutex); - inet_rcv_compat = NULL; - mutex_unlock(&sock_diag_table_mutex); + const struct sock_diag_inet_compat *old; + + old = xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, + NULL); + WARN_ON_ONCE(old != ptr); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); @@ -259,20 +261,27 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + const struct sock_diag_inet_compat *ptr; int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: - if (inet_rcv_compat == NULL) + + if (!rcu_access_pointer(inet_rcv_compat)) sock_load_diag_module(AF_INET, 0); - mutex_lock(&sock_diag_table_mutex); - if (inet_rcv_compat != NULL) - ret = inet_rcv_compat(skb, nlh); - else - ret = -EOPNOTSUPP; - mutex_unlock(&sock_diag_table_mutex); + rcu_read_lock(); + ptr = rcu_dereference(inet_rcv_compat); + if (ptr && !try_module_get(ptr->owner)) + ptr = NULL; + rcu_read_unlock(); + + ret = -EOPNOTSUPP; + if (ptr) { + ret = ptr->fn(skb, nlh); + module_put(ptr->owner); + } return ret; case SOCK_DIAG_BY_FAMILY: diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 52ce20691e4e..2c2d8b9dd8e9 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1527,6 +1527,11 @@ void inet_diag_unregister(const struct inet_diag_handler *h) } EXPORT_SYMBOL_GPL(inet_diag_unregister); +static const struct sock_diag_inet_compat inet_diag_compat = { + .owner = THIS_MODULE, + .fn = inet_diag_rcv_msg_compat, +}; + static int __init inet_diag_init(void) { const int inet_diag_table_size = (IPPROTO_MAX * @@ -1545,7 +1550,7 @@ static int __init inet_diag_init(void) if (err) goto out_free_inet; - sock_diag_register_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_register_inet_compat(&inet_diag_compat); out: return err; @@ -1560,7 +1565,7 @@ static void __exit inet_diag_exit(void) { sock_diag_unregister(&inet6_diag_handler); sock_diag_unregister(&inet_diag_handler); - sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_unregister_inet_compat(&inet_diag_compat); kfree(inet_diag_table); } -- cgit v1.2.3 From 7c05e7f3e74e7e550534d524e04d7e6f78d6fa24 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 5 Jan 2024 18:48:17 +0800 Subject: bpf: Support inlining bpf_kptr_xchg() helper The motivation of inlining bpf_kptr_xchg() comes from the performance profiling of bpf memory allocator benchmark. The benchmark uses bpf_kptr_xchg() to stash the allocated objects and to pop the stashed objects for free. After inling bpf_kptr_xchg(), the performance for object free on 8-CPUs VM increases about 2%~10%. The inline also has downside: both the kasan and kcsan checks on the pointer will be unavailable. bpf_kptr_xchg() can be inlined by converting the calling of bpf_kptr_xchg() into an atomic_xchg() instruction. But the conversion depends on two conditions: 1) JIT backend supports atomic_xchg() on pointer-sized word 2) For the specific arch, the implementation of xchg is the same as atomic_xchg() on pointer-sized words. It seems most 64-bit JIT backends satisfies these two conditions. But as a precaution, defining a weak function bpf_jit_supports_ptr_xchg() to state whether such conversion is safe and only supporting inline for 64-bit host. For x86-64, it supports BPF_XCHG atomic operation and both xchg() and atomic_xchg() use arch_xchg() to implement the exchange, so enabling the inline of bpf_kptr_xchg() on x86-64 first. Reviewed-by: Eduard Zingerman Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20240105104819.3916743-2-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- arch/x86/net/bpf_jit_comp.c | 5 +++++ include/linux/filter.h | 1 + kernel/bpf/core.c | 10 ++++++++++ kernel/bpf/helpers.c | 1 + kernel/bpf/verifier.c | 17 +++++++++++++++++ 5 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 919f647c740f..e1390d1e331b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -3242,3 +3242,8 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, BUG_ON(ret < 0); } } + +bool bpf_jit_supports_ptr_xchg(void) +{ + return true; +} diff --git a/include/linux/filter.h b/include/linux/filter.h index 68fb6c8142fe..35f067fd3840 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -955,6 +955,7 @@ bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); +bool bpf_jit_supports_ptr_xchg(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ea6843be2616..fbb1d95a9b44 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2925,6 +2925,16 @@ bool __weak bpf_jit_supports_far_kfunc_call(void) return false; } +/* Return TRUE if the JIT backend satisfies the following two conditions: + * 1) JIT backend supports atomic_xchg() on pointer-sized words. + * 2) Under the specific arch, the implementation of xchg() is the same + * as atomic_xchg() on pointer-sized words. + */ +bool __weak bpf_jit_supports_ptr_xchg(void) +{ + return false; +} + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index be72824f32b2..e04ca1af8927 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1414,6 +1414,7 @@ BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) { unsigned long *kptr = map_value; + /* This helper may be inlined by verifier. */ return xchg(kptr, (unsigned long)ptr); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65f598694d55..5b33d65eef7b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19809,6 +19809,23 @@ patch_map_ops_generic: continue; } + /* Implement bpf_kptr_xchg inline */ + if (prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_kptr_xchg && + bpf_jit_supports_ptr_xchg()) { + insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); + insn_buf[1] = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); + cnt = 2; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed -- cgit v1.2.3 From 522bb2c1f82b12eb7befaae815d1d959b8e6bba2 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 4 Jan 2024 16:09:05 -0800 Subject: bpf: support multiple tags per argument Add ability to iterate multiple decl_tag types pointed to the same function argument. Use this to support multiple __arg_xxx tags per global subprog argument. We leave btf_find_decl_tag_value() intact, but change its implementation to use a new btf_find_next_decl_tag() which can be straightforwardly used to find next BTF type ID of a matching btf_decl_tag type. btf_prepare_func_args() is switched from btf_find_decl_tag_value() to btf_find_next_decl_tag() to gain multiple tags per argument support. Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240105000909.2818934-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ kernel/bpf/btf.c | 64 ++++++++++++++++++++++++++++++++++------------------- 2 files changed, 43 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e30100597d0a..377857b232c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2472,6 +2472,8 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1636b574a63d..4f532b303a27 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3310,30 +3310,48 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } -const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, - int comp_idx, const char *tag_key) +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id) { - const char *value = NULL; - int i; + int len = strlen(tag_key); + int i, n; - for (i = 1; i < btf_nr_types(btf); i++) { + for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); - int len = strlen(tag_key); if (!btf_type_is_decl_tag(t)) continue; - if (pt != btf_type_by_id(btf, t->type) || - btf_type_decl_tag(t)->component_idx != comp_idx) + if (pt != btf_type_by_id(btf, t->type)) + continue; + if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; - /* Prevent duplicate entries for same type */ - if (value) - return ERR_PTR(-EEXIST); - value = __btf_name_by_offset(btf, t->name_off) + len; + return i; } - if (!value) - return ERR_PTR(-ENOENT); + return -ENOENT; +} + +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key) +{ + const char *value = NULL; + const struct btf_type *t; + int len, id; + + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, 0); + if (id < 0) + return ERR_PTR(id); + + t = btf_type_by_id(btf, id); + len = strlen(tag_key); + value = __btf_name_by_offset(btf, t->name_off) + len; + + /* Prevent duplicate entries for same type */ + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, id); + if (id >= 0) + return ERR_PTR(-EEXIST); + return value; } @@ -7032,20 +7050,16 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - const char *tag; u32 tags = 0; + int id = 0; - tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); - if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) { - tag = NULL; - } else if (IS_ERR(tag)) { - bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag)); - return PTR_ERR(tag); - } /* 'arg:' decl_tag takes precedence over derivation of * register type from BTF type itself */ - if (tag) { + while ((id = btf_find_next_decl_tag(btf, fn_t, i, "arg:", id)) > 0) { + const struct btf_type *tag_t = btf_type_by_id(btf, id); + const char *tag = __btf_name_by_offset(btf, tag_t->name_off) + 4; + /* disallow arg tags in static subprogs */ if (!is_global) { bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); @@ -7061,6 +7075,10 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) return -EOPNOTSUPP; } } + if (id != -ENOENT) { + bpf_log(log, "arg#%d type tag fetching failure: %d\n", i, id); + return id; + } t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) -- cgit v1.2.3 From 32f55dd4add4df1a5bc8febc1fafd3086290dbf6 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Mon, 8 Jan 2024 22:51:58 +0200 Subject: bpf: Make bpf_for_each_spilled_reg consider narrow spills Adjust the check in bpf_get_spilled_reg to take into account spilled registers narrower than 64 bits. That allows find_equal_scalars to properly adjust the range of all spilled registers that have the same ID. Before this change, it was possible for a register and a spilled register to have the same IDs but different ranges if the spill was narrower than 64 bits and a range check was performed on the register. Signed-off-by: Maxim Mikityanskiy Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240108205209.838365-5-maxtram95@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d07d857ca67f..e11baecbde68 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -453,7 +453,7 @@ struct bpf_verifier_state { #define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ + ((1 << frame->stack[slot].slot_type[BPF_REG_SIZE - 1]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -- cgit v1.2.3 From 3b1f89e747cd4b24244f2798a35d28815b744303 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:52 -0800 Subject: bpf: refactory struct_ops type initialization to a function. Move the majority of the code to bpf_struct_ops_init_one(), which can then be utilized for the initialization of newly registered dynamically allocated struct_ops types in the following patches. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-2-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/btf.h | 1 + kernel/bpf/bpf_struct_ops.c | 157 +++++++++++++++++++++++--------------------- kernel/bpf/btf.c | 5 ++ 3 files changed, 89 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index cf5c6ff48981..932af1680bb5 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -137,6 +137,7 @@ struct btf_struct_metas { extern const struct file_operations btf_fops; +const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02068bd0e4d9..96cba76f4ac3 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -110,102 +110,111 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { static const struct btf_type *module_type; -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, + struct btf *btf, + struct bpf_verifier_log *log) { - s32 type_id, value_id, module_id; const struct btf_member *member; - struct bpf_struct_ops *st_ops; const struct btf_type *t; + s32 type_id, value_id; char value_name[128]; const char *mname; - u32 i, j; + int i; - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); return; } - module_type = btf_type_by_id(btf, module_id); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return; + } - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", + for_each_member(i, t, member) { + const struct btf_type *func_proto; + + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", st_ops->name); - continue; + break; } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); - continue; + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + break; } - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - st_ops->name); - continue; - } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (func_proto && + btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + break; } + } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + if (i == btf_type_vlen(t)) { + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + } else { + st_ops->type_id = type_id; + st_ops->type = t; + st_ops->value_id = value_id; + st_ops->value_type = btf_type_by_id(btf, + value_id); + } + } +} - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +{ + struct bpf_struct_ops *st_ops; + s32 module_id; + u32 i; - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } + /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ +#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } - } + module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); + if (module_id < 0) { + pr_warn("Cannot find struct module in %s\n", btf_get_name(btf)); + return; + } + module_type = btf_type_by_id(btf, module_id); - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } - } + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + st_ops = bpf_struct_ops[i]; + bpf_struct_ops_init_one(st_ops, btf, log); } } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4f532b303a27..f8735a2ec5d4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1707,6 +1707,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); -- cgit v1.2.3 From 4c5763ed996a61b51d721d0968d0df957826ea49 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:54 -0800 Subject: bpf, net: introduce bpf_struct_ops_desc. Move some of members of bpf_struct_ops to bpf_struct_ops_desc. type_id is unavailabe in bpf_struct_ops anymore. Modules should get it from the btf received by kmod's init function. Cc: netdev@vger.kernel.org Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-4-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 15 +++++--- kernel/bpf/bpf_struct_ops.c | 80 ++++++++++++++++++++++-------------------- kernel/bpf/verifier.c | 8 +++-- net/bpf/bpf_dummy_struct_ops.c | 11 +++++- net/ipv4/bpf_tcp_ca.c | 8 ++++- 5 files changed, 73 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 377857b232c6..7fc95e7babab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1673,18 +1673,23 @@ struct bpf_struct_ops { void (*unreg)(void *kdata); int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); - const struct btf_type *type; - const struct btf_type *value_type; + void *cfi_stubs; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; +}; + +struct bpf_struct_ops_desc { + struct bpf_struct_ops *st_ops; + + const struct btf_type *type; + const struct btf_type *value_type; u32 type_id; u32 value_id; - void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); @@ -1728,7 +1733,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif #else -static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { return NULL; } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5b3ebcb435d0..9774f7824e8b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -32,7 +32,7 @@ struct bpf_struct_ops_value { struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -92,9 +92,9 @@ enum { __NR_BPF_STRUCT_OPS_TYPE, }; -static struct bpf_struct_ops * const bpf_struct_ops[] = { +static struct bpf_struct_ops_desc bpf_struct_ops[] = { #define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, + [BPF_STRUCT_OPS_TYPE_##_name] = { .st_ops = &bpf_##_name }, #include "bpf_struct_ops_types.h" #undef BPF_STRUCT_OPS_TYPE }; @@ -115,10 +115,11 @@ enum { IDX_MODULE_ID, }; -static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, - struct btf *btf, - struct bpf_verifier_log *log) +static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; const struct btf_type *t; s32 type_id, value_id; @@ -190,18 +191,18 @@ static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); + st_ops_desc->type_id = type_id; + st_ops_desc->type = t; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, + value_id); } } } void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { - struct bpf_struct_ops *st_ops; + struct bpf_struct_ops_desc *st_ops_desc; u32 i; /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ @@ -210,14 +211,14 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) #undef BPF_STRUCT_OPS_TYPE for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; - bpf_struct_ops_init_one(st_ops, btf, log); + st_ops_desc = &bpf_struct_ops[i]; + bpf_struct_ops_desc_init(st_ops_desc, btf, log); } } extern struct btf *btf_vmlinux; -static const struct bpf_struct_ops * +static const struct bpf_struct_ops_desc * bpf_struct_ops_find_value(u32 value_id) { unsigned int i; @@ -226,14 +227,14 @@ bpf_struct_ops_find_value(u32 value_id) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; + if (bpf_struct_ops[i].value_id == value_id) + return &bpf_struct_ops[i]; } return NULL; } -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { unsigned int i; @@ -241,8 +242,8 @@ const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; + if (bpf_struct_ops[i].type_id == type_id) + return &bpf_struct_ops[i]; } return NULL; @@ -302,7 +303,7 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; + const struct btf_type *t = st_map->st_ops_desc->type; u32 i; for (i = 0; i < btf_type_vlen(t); i++) { @@ -382,11 +383,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; + const struct btf_type *t = st_ops_desc->type; struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; @@ -399,7 +401,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_ops_desc->value_type, value); if (err) return err; @@ -492,7 +494,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -588,7 +590,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: @@ -669,22 +671,22 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; struct bpf_map *map; int ret; - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) + st_ops_desc = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) return ERR_PTR(-ENOTSUPP); - vt = st_ops->value_type; + vt = st_ops_desc->value_type; if (attr->value_size != vt->size) return ERR_PTR(-EINVAL); - t = st_ops->type; + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -696,7 +698,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) if (!st_map) return ERR_PTR(-ENOMEM); - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; ret = bpf_jit_charge_modmem(PAGE_SIZE); @@ -733,8 +735,8 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; - const struct btf_type *vt = st_ops->value_type; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; u64 usage; usage = sizeof(*st_map) + @@ -808,7 +810,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) /* st_link->map can be NULL if * bpf_struct_ops_link_create() fails to register. */ - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(&st_map->map); } kfree(st_link); @@ -855,7 +857,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; - if (!st_map->st_ops->update) + if (!st_map->st_ops_desc->st_ops->update) return -EOPNOTSUPP; mutex_lock(&update_mutex); @@ -868,12 +870,12 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); /* The new and old struct_ops must be the same type. */ - if (st_map->st_ops != old_st_map->st_ops) { + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { err = -EINVAL; goto err_out; } - err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); if (err) goto err_out; @@ -924,7 +926,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) if (err) goto err_out; - err = st_map->st_ops->reg(st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data); if (err) { bpf_link_cleanup(&link_primer); link = NULL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e9cc132dd02..e279491118b7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20285,6 +20285,7 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; @@ -20297,14 +20298,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 8906f7bdf4a9..ba2c58dba2da 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -22,6 +22,8 @@ struct bpf_dummy_ops_test_args { struct bpf_dummy_ops_state state; }; +static struct btf *bpf_dummy_ops_btf; + static struct bpf_dummy_ops_test_args * dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) { @@ -90,9 +92,15 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, void *image = NULL; unsigned int op_idx; int prog_ret; + s32 type_id; int err; - if (prog->aux->attach_btf_id != st_ops->type_id) + type_id = btf_find_by_name_kind(bpf_dummy_ops_btf, + bpf_bpf_dummy_ops.name, + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + if (prog->aux->attach_btf_id != type_id) return -EOPNOTSUPP; func_proto = prog->aux->attach_func_proto; @@ -148,6 +156,7 @@ out: static int bpf_dummy_init(struct btf *btf) { + bpf_dummy_ops_btf = btf; return 0; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e6896f..dffd8828079b 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; -- cgit v1.2.3 From 1338b93346587a2a6ac79bbcf55ef5b357745573 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:57 -0800 Subject: bpf: pass btf object id in bpf_map_info. Include btf object id (btf_obj_id) in bpf_map_info so that tools (ex: bpftools struct_ops dump) know the correct btf from the kernel to look up type information of struct_ops types. Since struct_ops types can be defined and registered in a module. The type information of a struct_ops type are defined in the btf of the module defining it. The userspace tools need to know which btf is for the module defining a struct_ops type. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-7-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 ++++ include/uapi/linux/bpf.h | 2 +- kernel/bpf/bpf_struct_ops.c | 7 +++++++ kernel/bpf/syscall.c | 2 ++ tools/include/uapi/linux/bpf.h | 2 +- 5 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7fc95e7babab..29fcae9fa8ed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1732,6 +1732,7 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { @@ -1759,6 +1760,9 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ +} #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5ddcca4c4fba..5e98af4fc2e2 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -947,3 +947,10 @@ err_out: kfree(link); return err; } + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 13193aaafb64..55b458429705 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4691,6 +4691,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From 689423db3bda2244c24db8a64de4cdb37be1de41 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:58 -0800 Subject: bpf: lookup struct_ops types from a given module BTF. This is a preparation for searching for struct_ops types from a specified module. BTF is always btf_vmlinux now. This patch passes a pointer of BTF to bpf_struct_ops_find_value() and bpf_struct_ops_find(). Once the new registration API of struct_ops types is used, other BTFs besides btf_vmlinux can also be passed to them. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-8-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 ++-- kernel/bpf/bpf_struct_ops.c | 11 ++++++----- kernel/bpf/verifier.c | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 29fcae9fa8ed..86ff8911d7ee 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1689,7 +1689,7 @@ struct bpf_struct_ops_desc { #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); @@ -1734,7 +1734,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, #endif void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) { return NULL; } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5e98af4fc2e2..7505f515aac3 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -221,11 +221,11 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) extern struct btf *btf_vmlinux; static const struct bpf_struct_ops_desc * -bpf_struct_ops_find_value(u32 value_id) +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) { unsigned int i; - if (!value_id || !btf_vmlinux) + if (!value_id || !btf) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { @@ -236,11 +236,12 @@ bpf_struct_ops_find_value(u32 value_id) return NULL; } -const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) { unsigned int i; - if (!type_id || !btf_vmlinux) + if (!type_id || !btf) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { @@ -682,7 +683,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) struct bpf_map *map; int ret; - st_ops_desc = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + st_ops_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id); if (!st_ops_desc) return ERR_PTR(-ENOTSUPP); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e279491118b7..2a0fd2ccdb11 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20298,7 +20298,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf_id = prog->aux->attach_btf_id; - st_ops_desc = bpf_struct_ops_find(btf_id); + st_ops_desc = bpf_struct_ops_find(btf_vmlinux, btf_id); if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); -- cgit v1.2.3 From e3f87fdfed7b770dd7066b02262b12747881e76d Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:00 -0800 Subject: bpf: hold module refcnt in bpf_struct_ops map creation and prog verification. To ensure that a module remains accessible whenever a struct_ops object of a struct_ops type provided by the module is still in use. struct bpf_struct_ops_map doesn't hold a refcnt to btf anymore since a module will hold a refcnt to it's btf already. But, struct_ops programs are different. They hold their associated btf, not the module since they need only btf to assure their types (signatures). However, verifier holds the refcnt of the associated module of a struct_ops type temporarily when verify a struct_ops prog. Verifier needs the help from the verifier operators (struct bpf_verifier_ops) provided by the owner module to verify data access of a prog, provide information, and generate code. This patch also add a count of links (links_cnt) to bpf_struct_ops_map. It avoids bpf_struct_ops_map_put_progs() from accessing btf after calling module_put() in bpf_struct_ops_map_free(). Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-10-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + kernel/bpf/bpf_struct_ops.c | 29 +++++++++++++++++++++++------ kernel/bpf/verifier.c | 11 +++++++++++ 4 files changed, 36 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 86ff8911d7ee..a5b425893d38 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1674,6 +1674,7 @@ struct bpf_struct_ops { int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); void *cfi_stubs; + struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e11baecbde68..7f5816482a10 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -662,6 +662,7 @@ struct bpf_verifier_env { u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; + struct module *attach_btf_mod; /* The owner module of prog->aux->attach_btf */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 3b8d689ece5d..02216a8d9265 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -40,6 +40,7 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; + u32 links_cnt; /* image is a page that has all the trampolines * that stores the func args before calling the bpf_prog. * A PAGE_SIZE "image" is enough to store all trampoline for @@ -306,10 +307,9 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops_desc->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { + for (i = 0; i < st_map->links_cnt; i++) { if (st_map->links[i]) { bpf_link_put(st_map->links[i]); st_map->links[i] = NULL; @@ -641,12 +641,20 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) bpf_jit_uncharge_modmem(PAGE_SIZE); } bpf_map_area_free(st_map->uvalue); - btf_put(st_map->btf); bpf_map_area_free(st_map); } static void bpf_struct_ops_map_free(struct bpf_map *map) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + /* The struct_ops's function may switch to another struct_ops. * * For example, bpf_tcp_cc_x->init() may switch to @@ -682,6 +690,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; struct btf *btf; int ret; @@ -695,11 +704,18 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) btf_put(btf); return ERR_PTR(-EINVAL); } + + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); } else { btf = bpf_get_btf_vmlinux(); if (IS_ERR(btf)) return ERR_CAST(btf); - btf_get(btf); } st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); @@ -746,8 +762,9 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) goto errout_free; } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->links_cnt = btf_type_vlen(t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->links_cnt * sizeof(struct bpf_links *), NUMA_NO_NODE); if (!st_map->uvalue || !st_map->links) { ret = -ENOMEM; @@ -763,7 +780,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) errout_free: __bpf_struct_ops_map_free(map); errout: - btf_put(btf); + module_put(mod); return ERR_PTR(ret); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6081512deb79..f31868ba0c2d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20299,6 +20299,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux(); + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } btf_id = prog->aux->attach_btf_id; st_ops_desc = bpf_struct_ops_find(btf, btf_id); @@ -21024,6 +21033,8 @@ err_release_maps: env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); -- cgit v1.2.3 From 612d087d4ba54cef47946e22e5dabad762dd7ed5 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:01 -0800 Subject: bpf: validate value_type A value_type should consist of three components: refcnt, state, and data. refcnt and state has been move to struct bpf_struct_ops_common_value to make it easier to check the value type. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-11-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 12 ++++++ kernel/bpf/bpf_struct_ops.c | 93 +++++++++++++++++++++++++++++---------------- 2 files changed, 72 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a5b425893d38..7c178170f93f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1688,6 +1688,18 @@ struct bpf_struct_ops_desc { u32 value_id; }; +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, + BPF_STRUCT_OPS_STATE_READY, +}; + +struct bpf_struct_ops_common_value { + refcount_t refcnt; + enum bpf_struct_ops_state state; +}; + #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02216a8d9265..30ab34fab0f8 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -13,19 +13,8 @@ #include #include -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, - BPF_STRUCT_OPS_STATE_READY, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state - struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; @@ -81,8 +70,8 @@ static DEFINE_MUTEX(update_mutex); #define BPF_STRUCT_OPS_TYPE(_name) \ extern struct bpf_struct_ops bpf_##_name; \ \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ +struct bpf_struct_ops_##_name { \ + struct bpf_struct_ops_common_value common; \ struct _name data ____cacheline_aligned_in_smp; \ }; #include "bpf_struct_ops_types.h" @@ -113,11 +102,49 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { BTF_ID_LIST(st_ops_ids) BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) enum { IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, }; +extern struct btf *btf_vmlinux; + +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) +{ + const struct btf_type *common_value_type; + const struct btf_member *member; + const struct btf_type *vt, *mt; + + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } + + return true; +} + static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) @@ -138,14 +165,6 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in %s\n", - value_name, btf_get_name(btf)); - return; - } - type_id = btf_find_by_name_kind(btf, st_ops->name, BTF_KIND_STRUCT); if (type_id < 0) { @@ -160,6 +179,16 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, return; } + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return; + for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -219,8 +248,6 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) } } -extern struct btf *btf_vmlinux; - static const struct bpf_struct_ops_desc * bpf_struct_ops_find_value(struct btf *btf, u32 value_id) { @@ -276,7 +303,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -287,7 +314,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; + uvalue->common.state = state; /* This value offers the user space a general estimate of how * many sockets are still utilizing this struct_ops for TCP @@ -295,7 +322,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, * should sufficiently meet our present goals. */ refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); - refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -413,7 +440,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -425,7 +452,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -540,7 +567,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * * Pair with smp_load_acquire() during lookup_elem(). */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); goto unlock; } @@ -558,7 +585,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -588,7 +615,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) if (st_map->map.map_flags & BPF_F_LINK) return -EOPNOTSUPP; - prev_state = cmpxchg(&st_map->kvalue.state, + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { @@ -848,7 +875,7 @@ static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && map->map_flags & BPF_F_LINK && /* Pair with smp_store_release() during map_update */ - smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; } static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) -- cgit v1.2.3 From f6be98d19985411ca1f3d53413d94d5b7f41c200 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:02 -0800 Subject: bpf, net: switch to dynamic registration Replace the static list of struct_ops types with per-btf struct_ops_tab to enable dynamic registration. Both bpf_dummy_ops and bpf_tcp_ca now utilize the registration function instead of being listed in bpf_struct_ops_types.h. Cc: netdev@vger.kernel.org Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-12-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 27 ++++++---- include/linux/btf.h | 12 +++++ kernel/bpf/bpf_struct_ops.c | 100 +++++--------------------------------- kernel/bpf/bpf_struct_ops_types.h | 12 ----- kernel/bpf/btf.c | 86 ++++++++++++++++++++++++++++++-- net/bpf/bpf_dummy_struct_ops.c | 11 ++++- net/ipv4/bpf_tcp_ca.c | 12 +++-- 7 files changed, 142 insertions(+), 118 deletions(-) delete mode 100644 kernel/bpf/bpf_struct_ops_types.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7c178170f93f..75b7f9b19c6a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1701,9 +1701,20 @@ struct bpf_struct_ops_common_value { }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +/* This macro helps developer to register a struct_ops type and generate + * type information correctly. Developers should use this macro to register + * a struct_ops type instead of calling __register_bpf_struct_ops() directly. + */ +#define register_bpf_struct_ops(st_ops, type) \ + ({ \ + struct bpf_struct_ops_##type { \ + struct bpf_struct_ops_common_value common; \ + struct type data ____cacheline_aligned_in_smp; \ + }; \ + BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ + __register_bpf_struct_ops(st_ops); \ + }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -1745,16 +1756,12 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - return NULL; -} -static inline void bpf_struct_ops_init(struct btf *btf, - struct bpf_verifier_log *log) -{ -} +#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); diff --git a/include/linux/btf.h b/include/linux/btf.h index 932af1680bb5..1ee8977b8c95 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -497,6 +497,18 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) struct bpf_verifier_log; +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +struct bpf_struct_ops; +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); +const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); +#else +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 30ab34fab0f8..defc052e4622 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -62,35 +62,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - struct bpf_struct_ops_common_value common; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops_desc bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = { .st_ops = &bpf_##_name }, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -145,9 +116,9 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } -static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, - struct btf *btf, - struct bpf_verifier_log *log) +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; @@ -161,7 +132,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, sizeof(value_name)) { pr_warn("struct_ops name %s is too long\n", st_ops->name); - return; + return -EINVAL; } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); @@ -170,13 +141,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (type_id < 0) { pr_warn("Cannot find struct %s in %s\n", st_ops->name, btf_get_name(btf)); - return; + return -EINVAL; } t = btf_type_by_id(btf, type_id); if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { pr_warn("Cannot support #%u members in struct %s\n", btf_type_vlen(t), st_ops->name); - return; + return -EINVAL; } value_id = btf_find_by_name_kind(btf, value_name, @@ -184,10 +155,10 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (value_id < 0) { pr_warn("Cannot find struct %s in %s\n", value_name, btf_get_name(btf)); - return; + return -EINVAL; } if (!is_valid_value_type(btf, value_id, t, value_name)) - return; + return -EINVAL; for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -196,13 +167,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!*mname) { pr_warn("anon member in struct %s is not supported\n", st_ops->name); - break; + return -EOPNOTSUPP; } if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); - break; + return -EOPNOTSUPP; } func_proto = btf_type_resolve_func_ptr(btf, @@ -214,7 +185,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, &st_ops->func_models[i])) { pr_warn("Error in parsing func ptr %s in struct %s\n", mname, st_ops->name); - break; + return -EINVAL; } } @@ -222,6 +193,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (st_ops->init(btf)) { pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); + return -EINVAL; } else { st_ops_desc->type_id = type_id; st_ops_desc->type = t; @@ -230,54 +202,8 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, value_id); } } -} -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) -{ - struct bpf_struct_ops_desc *st_ops_desc; - u32 i; - - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops_desc = &bpf_struct_ops[i]; - bpf_struct_ops_desc_init(st_ops_desc, btf, log); - } -} - -static const struct bpf_struct_ops_desc * -bpf_struct_ops_find_value(struct btf *btf, u32 value_id) -{ - unsigned int i; - - if (!value_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].value_id == value_id) - return &bpf_struct_ops[i]; - } - - return NULL; -} - -const struct bpf_struct_ops_desc * -bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - unsigned int i; - - if (!type_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].type_id == type_id) - return &bpf_struct_ops[i]; - } - - return NULL; + return 0; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2e5e6ec5d965..5c3e526a2dec 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -5972,8 +5973,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -8706,11 +8705,13 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } +#ifdef CONFIG_BPF_JIT static int -btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) { struct btf_struct_ops_tab *tab, *new_tab; - int i; + int i, err; tab = btf->struct_ops_tab; if (!tab) { @@ -8740,7 +8741,84 @@ btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + btf->struct_ops_tab->cnt++; return 0; } + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return -EINVAL; + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index ba2c58dba2da..02de71719aed 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include #include -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -256,7 +256,7 @@ static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { .test_sleepable = bpf_dummy_test_sleepable, }; -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -265,4 +265,11 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index dffd8828079b..8e7716256d3c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -345,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -356,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); -- cgit v1.2.3 From 6fe01d3cbb924a72493eb3f4722dfcfd1c194234 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:20:59 -0800 Subject: bpf: Add BPF token delegation mount options to BPF FS Add few new mount options to BPF FS that allow to specify that a given BPF FS instance allows creation of BPF token (added in the next patch), and what sort of operations are allowed under BPF token. As such, we get 4 new mount options, each is a bit mask - `delegate_cmds` allow to specify which bpf() syscall commands are allowed with BPF token derived from this BPF FS instance; - if BPF_MAP_CREATE command is allowed, `delegate_maps` specifies a set of allowable BPF map types that could be created with BPF token; - if BPF_PROG_LOAD command is allowed, `delegate_progs` specifies a set of allowable BPF program types that could be loaded with BPF token; - if BPF_PROG_LOAD command is allowed, `delegate_attachs` specifies a set of allowable BPF program attach types that could be loaded with BPF token; delegate_progs and delegate_attachs are meant to be used together, as full BPF program type is, in general, determined through both program type and program attach type. Currently, these mount options accept the following forms of values: - a special value "any", that enables all possible values of a given bit set; - numeric value (decimal or hexadecimal, determined by kernel automatically) that specifies a bit mask value directly; - all the values for a given mount option are combined, if specified multiple times. E.g., `mount -t bpf nodev /path/to/mount -o delegate_maps=0x1 -o delegate_maps=0x2` will result in a combined 0x3 mask. Ideally, more convenient (for humans) symbolic form derived from corresponding UAPI enums would be accepted (e.g., `-o delegate_progs=kprobe|tracepoint`) and I intend to implement this, but it requires a bunch of UAPI header churn, so I postponed it until this feature lands upstream or at least there is a definite consensus that this feature is acceptable and is going to make it, just to minimize amount of wasted effort and not increase amount of non-essential code to be reviewed. Attentive reader will notice that BPF FS is now marked as FS_USERNS_MOUNT, which theoretically makes it mountable inside non-init user namespace as long as the process has sufficient *namespaced* capabilities within that user namespace. But in reality we still restrict BPF FS to be mountable only by processes with CAP_SYS_ADMIN *in init userns* (extra check in bpf_fill_super()). FS_USERNS_MOUNT is added to allow creating BPF FS context object (i.e., fsopen("bpf")) from inside unprivileged process inside non-init userns, to capture that userns as the owning userns. It will still be required to pass this context object back to privileged process to instantiate and mount it. This manipulation is important, because capturing non-init userns as the owning userns of BPF FS instance (super block) allows to use that userns to constraint BPF token to that userns later on (see next patch). So creating BPF FS with delegation inside unprivileged userns will restrict derived BPF token objects to only "work" inside that intended userns, making it scoped to a intended "container". Also, setting these delegation options requires capable(CAP_SYS_ADMIN), so unprivileged process cannot set this up without involvement of a privileged process. There is a set of selftests at the end of the patch set that simulates this sequence of steps and validates that everything works as intended. But careful review is requested to make sure there are no missed gaps in the implementation and testing. This somewhat subtle set of aspects is the result of previous discussions ([0]) about various user namespace implications and interactions with BPF token functionality and is necessary to contain BPF token inside intended user namespace. [0] https://lore.kernel.org/bpf/20230704-hochverdient-lehne-eeb9eeef785e@brauner/ Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Christian Brauner Link: https://lore.kernel.org/bpf/20240124022127.2379740-3-andrii@kernel.org --- include/linux/bpf.h | 12 +++++++ kernel/bpf/inode.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 90 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75b7f9b19c6a..28374cec49df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1609,6 +1609,18 @@ struct bpf_link_primer { u32 id; }; +struct bpf_mount_opts { + kuid_t uid; + kgid_t gid; + umode_t mode; + + /* BPF token-related delegation options */ + u64 delegate_cmds; + u64 delegate_maps; + u64 delegate_progs; + u64 delegate_attachs; +}; + struct bpf_struct_ops_value; struct btf_member; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 41e0a55c35f5..70b748f6228c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "preload/bpf_preload.h" enum bpf_type { @@ -601,6 +602,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) { struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -610,6 +612,26 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + if (opts->delegate_cmds == ~0ULL) + seq_printf(m, ",delegate_cmds=any"); + else if (opts->delegate_cmds) + seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); + + if (opts->delegate_maps == ~0ULL) + seq_printf(m, ",delegate_maps=any"); + else if (opts->delegate_maps) + seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); + + if (opts->delegate_progs == ~0ULL) + seq_printf(m, ",delegate_progs=any"); + else if (opts->delegate_progs) + seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); + + if (opts->delegate_attachs == ~0ULL) + seq_printf(m, ",delegate_attachs=any"); + else if (opts->delegate_attachs) + seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); return 0; } @@ -635,28 +657,31 @@ enum { OPT_UID, OPT_GID, OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32 ("uid", OPT_UID), fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - kuid_t uid; - kgid_t gid; - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; kuid_t uid; kgid_t gid; - int opt; + int opt, err; + u64 msk; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -708,6 +733,28 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: + if (strcmp(param->string, "any") == 0) { + msk = ~0ULL; + } else { + err = kstrtou64(param->string, 0, &msk); + if (err) + return err; + } + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + switch (opt) { + case OPT_DELEGATE_CMDS: opts->delegate_cmds |= msk; break; + case OPT_DELEGATE_MAPS: opts->delegate_maps |= msk; break; + case OPT_DELEGATE_PROGS: opts->delegate_progs |= msk; break; + case OPT_DELEGATE_ATTACHS: opts->delegate_attachs |= msk; break; + default: return -EINVAL; + } + break; } return 0; @@ -784,10 +831,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -811,7 +862,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -835,17 +886,32 @@ static int bpf_init_fs_context(struct fs_context *fc) opts->uid = current_fsuid(); opts->gid = current_fsgid(); - fc->fs_private = opts; + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; + + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_litter_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) -- cgit v1.2.3 From 35f96de04127d332a5c5e8a155d31f452f88c76d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:00 -0800 Subject: bpf: Introduce BPF token object Add new kind of BPF kernel object, BPF token. BPF token is meant to allow delegating privileged BPF functionality, like loading a BPF program or creating a BPF map, from privileged process to a *trusted* unprivileged process, all while having a good amount of control over which privileged operations could be performed using provided BPF token. This is achieved through mounting BPF FS instance with extra delegation mount options, which determine what operations are delegatable, and also constraining it to the owning user namespace (as mentioned in the previous patch). BPF token itself is just a derivative from BPF FS and can be created through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF FS FD, which can be attained through open() API by opening BPF FS mount point. Currently, BPF token "inherits" delegated command, map types, prog type, and attach type bit sets from BPF FS as is. In the future, having an BPF token as a separate object with its own FD, we can allow to further restrict BPF token's allowable set of things either at the creation time or after the fact, allowing the process to guard itself further from unintentionally trying to load undesired kind of BPF programs. But for now we keep things simple and just copy bit sets as is. When BPF token is created from BPF FS mount, we take reference to the BPF super block's owning user namespace, and then use that namespace for checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN} capabilities that are normally only checked against init userns (using capable()), but now we check them using ns_capable() instead (if BPF token is provided). See bpf_token_capable() for details. Such setup means that BPF token in itself is not sufficient to grant BPF functionality. User namespaced process has to *also* have necessary combination of capabilities inside that user namespace. So while previously CAP_BPF was useless when granted within user namespace, now it gains a meaning and allows container managers and sys admins to have a flexible control over which processes can and need to use BPF functionality within the user namespace (i.e., container in practice). And BPF FS delegation mount options and derived BPF tokens serve as a per-container "flag" to grant overall ability to use bpf() (plus further restrict on which parts of bpf() syscalls are treated as namespaced). Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF) within the BPF FS owning user namespace, rounding up the ns_capable() story of BPF token. Also creating BPF token in init user namespace is currently not supported, given BPF token doesn't have any effect in init user namespace anyways. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Christian Brauner Link: https://lore.kernel.org/bpf/20240124022127.2379740-4-andrii@kernel.org --- include/linux/bpf.h | 41 ++++++++ include/uapi/linux/bpf.h | 37 +++++++ kernel/bpf/Makefile | 2 +- kernel/bpf/inode.c | 12 ++- kernel/bpf/syscall.c | 17 ++++ kernel/bpf/token.c | 217 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 37 +++++++ 7 files changed, 357 insertions(+), 6 deletions(-) create mode 100644 kernel/bpf/token.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 28374cec49df..d9ff7ce547b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -52,6 +52,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1621,6 +1625,13 @@ struct bpf_mount_opts { u64 delegate_attachs; }; +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; +}; + struct bpf_struct_ops_value; struct btf_member; @@ -2109,6 +2120,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2243,6 +2255,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; +bool bpf_token_capable(const struct bpf_token *token, int cap); + static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); @@ -2277,8 +2291,17 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2638,6 +2661,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 70b748f6228c..565be1f3f1ea 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -99,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -603,6 +603,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + u64 mask; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -613,7 +614,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); - if (opts->delegate_cmds == ~0ULL) + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((opts->delegate_cmds & mask) == mask) seq_printf(m, ",delegate_cmds=any"); else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); @@ -646,7 +648,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d5f1edee2d50..3ecba592b8ed 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5426,6 +5426,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5559,6 +5573,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..bdb6fe697568 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,217 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool bpf_ns_capable(struct user_namespace *ns, int cap) +{ + return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); +} + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + struct user_namespace *userns; + + /* BPF token allows ns_capable() level of capabilities */ + userns = token ? token->userns : &init_user_ns; + if (!bpf_ns_capable(userns, cap)) + return false; + return true; +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + put_user_ns(token->userns); + kfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + /* Creating BPF token in init_user_ns doesn't make much sense. */ + if (current_user_ns() == &init_user_ns) { + err = -EOPNOTSUPP; + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + mnt_opts = path.dentry->d_sb->s_fs_info; + token->allowed_cmds = mnt_opts->delegate_cmds; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + if (!token) + return false; + return token->allowed_cmds & (1ULL << cmd); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From a177fc2bf6fd83704854feaf7aae926b1df4f0b9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:01 -0800 Subject: bpf: Add BPF token support to BPF_MAP_CREATE command Allow providing token_fd for BPF_MAP_CREATE command to allow controlled BPF map creation from unprivileged process through delegated BPF token. New BPF_F_TOKEN_FD flag is added to specify together with BPF token FD for BPF_MAP_CREATE command. Wire through a set of allowed BPF map types to BPF token, derived from BPF FS at BPF token creation time. This, in combination with allowed_cmds allows to create a narrowly-focused BPF token (controlled by privileged agent) with a restrictive set of BPF maps that application can attempt to create. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-5-andrii@kernel.org --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 8 +++ kernel/bpf/inode.c | 3 +- kernel/bpf/syscall.c | 59 +++++++++++++++++----- kernel/bpf/token.c | 16 ++++++ tools/include/uapi/linux/bpf.h | 8 +++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 ++ 8 files changed, 86 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d9ff7ce547b4..8252452d0c4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1630,6 +1630,7 @@ struct bpf_token { atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; + u64 allowed_maps; }; struct bpf_struct_ops_value; @@ -2297,6 +2298,7 @@ int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 565be1f3f1ea..034b7e4d8f19 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -620,7 +620,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); - if (opts->delegate_maps == ~0ULL) + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((opts->delegate_maps & mask) == mask) seq_printf(m, ",delegate_maps=any"); else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3ecba592b8ed..b13a4bdcd3a0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1128,14 +1128,16 @@ static bool bpf_net_capable(void) return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } -#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -1143,6 +1145,12 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it + * to avoid per-map type checks tripping on unknown flag + */ + token_flag = attr->map_flags & BPF_F_TOKEN_FD; + attr->map_flags &= ~BPF_F_TOKEN_FD; + if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) @@ -1183,14 +1191,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (token_flag) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1223,25 +1249,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!bpf_net_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1278,7 +1306,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1299,6 +1327,7 @@ static int map_create(union bpf_attr *attr) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1319,6 +1348,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bdb6fe697568..bc86be4ca567 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -73,6 +73,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -168,6 +175,7 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -215,3 +223,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) return false; return token->allowed_cmds & (1ULL << cmd); } + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..573249a2814d 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index eb34d612d6f8..1f328c0d8aff 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); -- cgit v1.2.3 From caf8f28e036c4ba1e823355da6c0c01c39e70ab9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:03 -0800 Subject: bpf: Add BPF token support to BPF_PROG_LOAD command Add basic support of BPF token to BPF_PROG_LOAD. BPF_F_TOKEN_FD flag should be set in prog_flags field when providing prog_token_fd. Wire through a set of allowed BPF program types and attach types, derived from BPF FS at BPF token creation time. Then make sure we perform bpf_token_capable() checks everywhere where it's relevant. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-7-andrii@kernel.org --- include/linux/bpf.h | 6 ++ include/uapi/linux/bpf.h | 5 ++ kernel/bpf/core.c | 1 + kernel/bpf/inode.c | 6 +- kernel/bpf/syscall.c | 90 ++++++++++++++++------ kernel/bpf/token.c | 27 +++++++ tools/include/uapi/linux/bpf.h | 5 ++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 + 9 files changed, 118 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8252452d0c4d..d0bf37e3f166 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1489,6 +1489,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1631,6 +1632,8 @@ struct bpf_token { struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; }; struct bpf_struct_ops_value; @@ -2299,6 +2302,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fbb1d95a9b44..00dccba29769 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2779,6 +2779,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 034b7e4d8f19..5fb10da5717f 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -626,12 +626,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); - if (opts->delegate_progs == ~0ULL) + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) seq_printf(m, ",delegate_progs=any"); else if (opts->delegate_progs) seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); - if (opts->delegate_attachs == ~0ULL) + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) seq_printf(m, ",delegate_attachs=any"); else if (opts->delegate_attachs) seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45b3a55896eb..61b4bf4cc287 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2626,13 +2626,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2646,13 +2648,35 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | - BPF_F_TEST_REG_INVARIANTS)) + BPF_F_TEST_REG_INVARIANTS | + BPF_F_TOKEN_FD)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2661,21 +2685,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !bpf_net_capable()) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2685,27 +2711,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2713,7 +2745,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2723,7 +2756,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2734,6 +2768,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; @@ -2851,6 +2889,8 @@ free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3858,7 +3898,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_net_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bc86be4ca567..c13c73788d8c 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -80,6 +80,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -176,6 +190,8 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -231,3 +247,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t return token->allowed_maps & (1ULL << type); } + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 573249a2814d..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 1f328c0d8aff..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); -- cgit v1.2.3 From bbc1d24724e110b86a1a7c3c1724ce0d62cc1e2e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:04 -0800 Subject: bpf: Take into account BPF token when fetching helper protos Instead of performing unconditional system-wide bpf_capable() and perfmon_capable() calls inside bpf_base_func_proto() function (and other similar ones) to determine eligibility of a given BPF helper for a given program, use previously recorded BPF token during BPF_PROG_LOAD command handling to inform the decision. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-8-andrii@kernel.org --- drivers/media/rc/bpf-lirc.c | 2 +- include/linux/bpf.h | 5 +++-- kernel/bpf/cgroup.c | 6 +++--- kernel/bpf/helpers.c | 6 +++--- kernel/bpf/syscall.c | 5 +++-- kernel/trace/bpf_trace.c | 2 +- net/core/filter.c | 32 ++++++++++++++++---------------- net/ipv4/bpf_tcp_ca.c | 2 +- net/netfilter/nf_bpf_link.c | 2 +- 9 files changed, 32 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e81..6d07693c6b9f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: - if (perfmon_capable()) + if (bpf_token_capable(prog->aux->token, CAP_PERFMON)) return bpf_get_trace_printk_proto(); fallthrough; default: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0bf37e3f166..1325225bf602 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2550,7 +2550,8 @@ int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); -const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); @@ -2810,7 +2811,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log, } static inline const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 491d20038cbe..98e0e3835b28 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e04ca1af8927..bcb951a2ecf4 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1680,7 +1680,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1731,7 +1731,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1789,7 +1789,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 61b4bf4cc287..f76408c957ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5772,7 +5772,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5822,7 +5822,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c98c20abaf99..64fdaf79d113 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/core/filter.c b/net/core/filter.c index 6a7abbaa50b8..521bcd0f5e4d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,7 +87,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id); +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) @@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id) +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; @@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 8e7716256d3c..834edc18463a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -197,7 +197,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 0e4beae421f8..5257d5e7eb09 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { -- cgit v1.2.3 From d79a3549754725bb90e58104417449edddf3da3d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:05 -0800 Subject: bpf: Consistently use BPF token throughout BPF verifier logic Remove remaining direct queries to perfmon_capable() and bpf_capable() in BPF verifier logic and instead use BPF token (if available) to make decisions about privileges. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-9-andrii@kernel.org --- include/linux/bpf.h | 16 ++++++++-------- include/linux/filter.h | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/core.c | 2 +- kernel/bpf/verifier.c | 13 ++++++------- net/core/filter.c | 4 ++-- 6 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1325225bf602..4e146e9708be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2261,24 +2261,24 @@ extern int sysctl_unprivileged_bpf_disabled; bool bpf_token_capable(const struct bpf_token *token, int cap); -static inline bool bpf_allow_ptr_leaks(void) +static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_allow_uninit_stack(void) +static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v1(void) +static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v4(void) +static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index 35f067fd3840..fee070b9826e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1140,7 +1140,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && bpf_capable()) + if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0bdbbbeab155..13358675ff2e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 00dccba29769..71c459a51d9e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -682,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f31868ba0c2d..fe833e831cb6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20830,7 +20830,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -20862,12 +20867,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; diff --git a/net/core/filter.c b/net/core/filter.c index 521bcd0f5e4d..40121475e8d1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } @@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: -- cgit v1.2.3 From 1b67772e4e3f16cd647b229cae95fc06d120be08 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:06 -0800 Subject: bpf,lsm: Refactor bpf_prog_alloc/bpf_prog_free LSM hooks Based on upstream discussion ([0]), rework existing bpf_prog_alloc_security LSM hook. Rename it to bpf_prog_load and instead of passing bpf_prog_aux, pass proper bpf_prog pointer for a full BPF program struct. Also, we pass bpf_attr union with all the user-provided arguments for BPF_PROG_LOAD command. This will give LSMs as much information as we can basically provide. The hook is also BPF token-aware now, and optional bpf_token struct is passed as a third argument. bpf_prog_load LSM hook is called after a bunch of sanity checks were performed, bpf_prog and bpf_prog_aux were allocated and filled out, but right before performing full-fledged BPF verification step. bpf_prog_free LSM hook is now accepting struct bpf_prog argument, for consistency. SELinux code is adjusted to all new names, types, and signatures. Note, given that bpf_prog_load (previously bpf_prog_alloc) hook can be used by some LSMs to allocate extra security blob, but also by other LSMs to reject BPF program loading, we need to make sure that bpf_prog_free LSM hook is called after bpf_prog_load/bpf_prog_alloc one *even* if the hook itself returned error. If we don't do that, we run the risk of leaking memory. This seems to be possible today when combining SELinux and BPF LSM, as one example, depending on their relative ordering. Also, for BPF LSM setup, add bpf_prog_load and bpf_prog_free to sleepable LSM hooks list, as they are both executed in sleepable context. Also drop bpf_prog_load hook from untrusted, as there is no issue with refcount or anything else anymore, that originally forced us to add it to untrusted list in c0c852dd1876 ("bpf: Do not mark certain LSM hook arguments as trusted"). We now trigger this hook much later and it should not be an issue anymore. [0] https://lore.kernel.org/bpf/9fe88aef7deabbe87d3fc38c4aea3c69.paul@paul-moore.com/ Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-10-andrii@kernel.org --- include/linux/lsm_hook_defs.h | 5 +++-- include/linux/security.h | 12 +++++++----- kernel/bpf/bpf_lsm.c | 5 +++-- kernel/bpf/syscall.c | 25 +++++++++++++------------ security/security.c | 25 +++++++++++++++---------- security/selinux/hooks.c | 15 ++++++++------- 6 files changed, 49 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 185924c56378..370181aa685b 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -406,8 +406,9 @@ LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) -LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) -LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) +LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index d0eb20f90b26..cb2932fce448 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2064,15 +2064,16 @@ static inline void securityfs_remove(struct dentry *dentry) union bpf_attr; struct bpf_map; struct bpf_prog; -struct bpf_prog_aux; +struct bpf_token; #ifdef CONFIG_SECURITY extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); extern int security_bpf_map_alloc(struct bpf_map *map); extern void security_bpf_map_free(struct bpf_map *map); -extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); -extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token); +extern void security_bpf_prog_free(struct bpf_prog *prog); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2098,12 +2099,13 @@ static inline int security_bpf_map_alloc(struct bpf_map *map) static inline void security_bpf_map_free(struct bpf_map *map) { } -static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { return 0; } -static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +static inline void security_bpf_prog_free(struct bpf_prog *prog) { } #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e8e910395bf6..7ee0dd011de4 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -263,6 +263,8 @@ BTF_ID(func, bpf_lsm_bpf_map) BTF_ID(func, bpf_lsm_bpf_map_alloc_security) BTF_ID(func, bpf_lsm_bpf_map_free_security) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -358,8 +360,7 @@ BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f76408c957ce..3857a2a9ae7f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2180,7 +2180,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2772,10 +2772,6 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->token = token; token = NULL; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; - prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2783,12 +2779,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog_sec; + goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2802,14 +2798,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog_sec; + goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; } /* @@ -2831,12 +2827,16 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token); + if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2882,10 +2882,11 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); diff --git a/security/security.c b/security/security.c index 0144a98d3712..eb159da4b146 100644 --- a/security/security.c +++ b/security/security.c @@ -5423,16 +5423,21 @@ int security_bpf_map_alloc(struct bpf_map *map) } /** - * security_bpf_prog_alloc() - Allocate a bpf program LSM blob - * @aux: bpf program aux info struct + * security_bpf_prog_load() - Check if loading of BPF program is allowed + * @prog: BPF program object + * @attr: BPF syscall attributes used to create BPF program + * @token: BPF token used to grant user access to BPF subsystem * - * Initialize the security field inside bpf program. + * Perform an access control check when the kernel loads a BPF program and + * allocates associated BPF program object. This hook is also responsible for + * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_prog_alloc_security, 0, aux); + return call_int_hook(bpf_prog_load, 0, prog, attr, token); } /** @@ -5447,14 +5452,14 @@ void security_bpf_map_free(struct bpf_map *map) } /** - * security_bpf_prog_free() - Free a bpf program's LSM blob - * @aux: bpf program aux info struct + * security_bpf_prog_free() - Free a BPF program's LSM blob + * @prog: BPF program struct * - * Clean up the security information stored inside bpf prog. + * Clean up the security information stored inside BPF program. */ -void security_bpf_prog_free(struct bpf_prog_aux *aux) +void security_bpf_prog_free(struct bpf_prog *prog) { - call_void_hook(bpf_prog_free_security, aux); + call_void_hook(bpf_prog_free, prog); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a6bf90ace84c..6d64fb189b1b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6942,7 +6942,8 @@ static void selinux_bpf_map_free(struct bpf_map *map) kfree(bpfsec); } -static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6951,16 +6952,16 @@ static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) return -ENOMEM; bpfsec->sid = current_sid(); - aux->security = bpfsec; + prog->aux->security = bpfsec; return 0; } -static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +static void selinux_bpf_prog_free(struct bpf_prog *prog) { - struct bpf_security_struct *bpfsec = aux->security; + struct bpf_security_struct *bpfsec = prog->aux->security; - aux->security = NULL; + prog->aux->security = NULL; kfree(bpfsec); } #endif @@ -7325,7 +7326,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), - LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), #endif #ifdef CONFIG_PERF_EVENTS @@ -7383,7 +7384,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), - LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), -- cgit v1.2.3 From a2431c7eabcf9bd5a1e7a1f7ecded40fdda4a8c5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:07 -0800 Subject: bpf,lsm: Refactor bpf_map_alloc/bpf_map_free LSM hooks Similarly to bpf_prog_alloc LSM hook, rename and extend bpf_map_alloc hook into bpf_map_create, taking not just struct bpf_map, but also bpf_attr and bpf_token, to give a fuller context to LSMs. Unlike bpf_prog_alloc, there is no need to move the hook around, as it currently is firing right before allocating BPF map ID and FD, which seems to be a sweet spot. But like bpf_prog_alloc/bpf_prog_free combo, make sure that bpf_map_free LSM hook is called even if bpf_map_create hook returned error, as if few LSMs are combined together it could be that one LSM successfully allocated security blob for its needs, while subsequent LSM rejected BPF map creation. The former LSM would still need to free up LSM blob, so we need to ensure security_bpf_map_free() is called regardless of the outcome. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-11-andrii@kernel.org --- include/linux/lsm_hook_defs.h | 5 +++-- include/linux/security.h | 6 ++++-- kernel/bpf/bpf_lsm.c | 6 +++--- kernel/bpf/syscall.c | 4 ++-- security/security.c | 16 ++++++++++------ security/selinux/hooks.c | 7 ++++--- 6 files changed, 26 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 370181aa685b..1be4d3ca6efb 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -404,8 +404,9 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) -LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) diff --git a/include/linux/security.h b/include/linux/security.h index cb2932fce448..83fcdc974116 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2069,7 +2069,8 @@ struct bpf_token; extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); -extern int security_bpf_map_alloc(struct bpf_map *map); +extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token); extern void security_bpf_map_free(struct bpf_map *map); extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); @@ -2091,7 +2092,8 @@ static inline int security_bpf_prog(struct bpf_prog *prog) return 0; } -static inline int security_bpf_map_alloc(struct bpf_map *map) +static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { return 0; } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 7ee0dd011de4..76976908b302 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,8 +260,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bpf_prog_load) BTF_ID(func, bpf_lsm_bpf_prog_free) @@ -359,7 +359,7 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3857a2a9ae7f..b2750b79ac80 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1318,9 +1318,9 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) diff --git a/security/security.c b/security/security.c index eb159da4b146..26fcab35b6cd 100644 --- a/security/security.c +++ b/security/security.c @@ -5410,16 +5410,20 @@ int security_bpf_prog(struct bpf_prog *prog) } /** - * security_bpf_map_alloc() - Allocate a bpf map LSM blob - * @map: bpf map + * security_bpf_map_create() - Check if BPF map creation is allowed + * @map: BPF map object + * @attr: BPF syscall attributes used to create BPF map + * @token: BPF token used to grant user access * - * Initialize the security field inside bpf map. + * Do a check when the kernel creates a new BPF map. This is also the + * point where LSM blob is allocated for LSMs that need them. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_map_alloc(struct bpf_map *map) +int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_map_alloc_security, 0, map); + return call_int_hook(bpf_map_create, 0, map, attr, token); } /** @@ -5448,7 +5452,7 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, */ void security_bpf_map_free(struct bpf_map *map) { - call_void_hook(bpf_map_free_security, map); + call_void_hook(bpf_map_free, map); } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6d64fb189b1b..3d336a7952f7 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6920,7 +6920,8 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static int selinux_bpf_map_alloc(struct bpf_map *map) +static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -7325,7 +7326,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), - LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), #endif @@ -7383,7 +7384,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL - LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), + LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), #endif #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3 From f568a3d49af9aed813a184353592efe29b0e3d16 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:08 -0800 Subject: bpf,lsm: Add BPF token LSM hooks Wire up bpf_token_create and bpf_token_free LSM hooks, which allow to allocate LSM security blob (we add `void *security` field to struct bpf_token for that), but also control who can instantiate BPF token. This follows existing pattern for BPF map and BPF prog. Also add security_bpf_token_allow_cmd() and security_bpf_token_capable() LSM hooks that allow LSM implementation to control and negate (if necessary) BPF token's delegation of a specific bpf_cmd and capability, respectively. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-12-andrii@kernel.org --- include/linux/bpf.h | 3 +++ include/linux/lsm_hook_defs.h | 5 ++++ include/linux/security.h | 25 ++++++++++++++++++ kernel/bpf/bpf_lsm.c | 4 +++ kernel/bpf/token.c | 12 ++++++++- security/security.c | 60 +++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 108 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4e146e9708be..b86bd15a051d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1634,6 +1634,9 @@ struct bpf_token { u64 allowed_maps; u64 allowed_progs; u64 allowed_attachs; +#ifdef CONFIG_SECURITY + void *security; +#endif }; struct bpf_struct_ops_value; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 1be4d3ca6efb..cd6fbc7af3f8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -410,6 +410,11 @@ LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) +LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, + struct path *path) +LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) +LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) +LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index 83fcdc974116..15804af54f37 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include #include #include +#include #include struct linux_binprm; @@ -2075,6 +2076,11 @@ extern void security_bpf_map_free(struct bpf_map *map); extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); extern void security_bpf_prog_free(struct bpf_prog *prog); +extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path); +extern void security_bpf_token_free(struct bpf_token *token); +extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +extern int security_bpf_token_capable(const struct bpf_token *token, int cap); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2109,6 +2115,25 @@ static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr * static inline void security_bpf_prog_free(struct bpf_prog *prog) { } + +static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return 0; +} + +static inline void security_bpf_token_free(struct bpf_token *token) +{ } + +static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return 0; +} + +static inline int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 76976908b302..63b4dc495125 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -265,6 +265,10 @@ BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bpf_prog_load) BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index c13c73788d8c..64c568f47f69 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -7,6 +7,7 @@ #include #include #include +#include static bool bpf_ns_capable(struct user_namespace *ns, int cap) { @@ -21,6 +22,8 @@ bool bpf_token_capable(const struct bpf_token *token, int cap) userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; + if (token && security_bpf_token_capable(token, cap) < 0) + return false; return true; } @@ -31,6 +34,7 @@ void bpf_token_inc(struct bpf_token *token) static void bpf_token_free(struct bpf_token *token) { + security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } @@ -193,6 +197,10 @@ int bpf_token_create(union bpf_attr *attr) token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; + err = security_bpf_token_create(token, attr, &path); + if (err) + goto out_token; + fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; @@ -237,7 +245,9 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; - return token->allowed_cmds & (1ULL << cmd); + if (!(token->allowed_cmds & (1ULL << cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) diff --git a/security/security.c b/security/security.c index 26fcab35b6cd..73e009e3d937 100644 --- a/security/security.c +++ b/security/security.c @@ -5444,6 +5444,55 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, return call_int_hook(bpf_prog_load, 0, prog, attr, token); } +/** + * security_bpf_token_create() - Check if creating of BPF token is allowed + * @token: BPF token object + * @attr: BPF syscall attributes used to create BPF token + * @path: path pointing to BPF FS mount point from which BPF token is created + * + * Do a check when the kernel instantiates a new BPF token object from BPF FS + * instance. This is also the point where LSM blob can be allocated for LSMs. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return call_int_hook(bpf_token_create, 0, token, attr, path); +} + +/** + * security_bpf_token_cmd() - Check if BPF token is allowed to delegate + * requested BPF syscall command + * @token: BPF token object + * @cmd: BPF syscall command requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF syscall command. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return call_int_hook(bpf_token_cmd, 0, token, cmd); +} + +/** + * security_bpf_token_capable() - Check if BPF token is allowed to delegate + * requested BPF-related capability + * @token: BPF token object + * @cap: capabilities requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF-related capabilities. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return call_int_hook(bpf_token_capable, 0, token, cap); +} + /** * security_bpf_map_free() - Free a bpf map's LSM blob * @map: bpf map @@ -5465,6 +5514,17 @@ void security_bpf_prog_free(struct bpf_prog *prog) { call_void_hook(bpf_prog_free, prog); } + +/** + * security_bpf_token_free() - Free a BPF token's LSM blob + * @token: BPF token struct + * + * Clean up the security information stored inside BPF token. + */ +void security_bpf_token_free(struct bpf_token *token) +{ + call_void_hook(bpf_token_free, token); +} #endif /* CONFIG_BPF_SYSCALL */ /** -- cgit v1.2.3 From 83e897a961b801536dd1d736e9ede5b1ddb1c188 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 2 Jan 2024 21:35:33 +0200 Subject: wifi: ieee80211: add definitions for negotiated TID to Link map Add the relevant definitions and structures for TID to Link mapping negotiation request/response/teardown according to P802.11be_D4.0. Signed-off-by: Ayala Beker Reviewed-by: Gregory Greenman Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://msgid.link/20240102213313.9ef2b866c8c7.Ieaf7dadea9961e0edc55d19c99f0f9fbae591de6@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 83c4d060a559..eafa70e5ba94 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1454,6 +1454,20 @@ struct ieee80211_mgmt { u8 max_tod_error; u8 max_toa_error; } __packed wnm_timing_msr; + struct { + u8 action_code; + u8 dialog_token; + u8 variable[]; + } __packed ttlm_req; + struct { + u8 action_code; + u8 dialog_token; + u8 status_code; + u8 variable[]; + } __packed ttlm_res; + struct { + u8 action_code; + } __packed ttlm_tear_down; } u; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ @@ -3357,6 +3371,8 @@ enum ieee80211_statuscode { WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, WLAN_STATUS_SAE_PK = 127, + WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING = 133, + WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED = 134, }; @@ -3682,6 +3698,7 @@ enum ieee80211_category { WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VHT = 21, WLAN_CATEGORY_S1G = 22, + WLAN_CATEGORY_PROTECTED_EHT = 37, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; @@ -3745,6 +3762,13 @@ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; +/* Protected EHT action codes */ +enum ieee80211_protected_eht_actioncode { + WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, + WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, + WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, +}; + /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -4845,6 +4869,10 @@ struct ieee80211_multi_link_elem { #define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f #define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 #define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP 0 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME 1 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED 2 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 #define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 #define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 -- cgit v1.2.3 From f7660b3f584aadd25dde18aa1902488577a15863 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Tue, 2 Jan 2024 21:35:37 +0200 Subject: wifi: mac80211: add support for negotiated TTLM request Update neg_ttlm and active_links according to the new mapping, and send a negotiated TID-to-link map request with the new mapping. Signed-off-by: Ayala Beker Reviewed-by: Gregory Greenman Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://msgid.link/20240102213313.eeb385d771df.I2a5441c14421de884dbd93d1624ce7bb2c944833@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 37 +++++++++++++++ include/net/mac80211.h | 7 ++- net/mac80211/cfg.c | 12 +++++ net/mac80211/ieee80211_i.h | 8 ++++ net/mac80211/iface.c | 4 ++ net/mac80211/mlme.c | 114 +++++++++++++++++++++++++++++++++++++++++++++ net/mac80211/rx.c | 8 ++++ 7 files changed, 188 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index eafa70e5ba94..f0c068446c79 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -5024,6 +5024,43 @@ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) return get_unaligned_le16(common); } +/** + * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. + * @data: pointer to the multi link EHT IE + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + * + * If the MLD capabilities and operations field is not present, 0 will be + * returned. + */ +static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + + return get_unaligned_le16(common); +} + /** * ieee80211_mle_size_ok - validate multi-link element size * @data: pointer to the element data diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 6490b92d5cc1..84cc66dd93c1 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1810,9 +1810,11 @@ enum ieee80211_offload_flags { * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. * @aid: association ID number, valid only when @assoc is true - * @eml_cap: EML capabilities as described in P802.11be_D2.2 Figure 9-1002k. + * @eml_cap: EML capabilities as described in P802.11be_D4.1 Figure 9-1001j. * @eml_med_sync_delay: Medium Synchronization delay as described in - * P802.11be_D2.2 Figure 9-1002j. + * P802.11be_D4.1 Figure 9-1001i. + * @mld_capa_op: MLD Capabilities and Operations per P802.11be_D4.1 + * Figure 9-1001k * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The * may filter ARP queries targeted for other addresses than listed here. * The driver must allow ARP queries targeted for all address listed here @@ -1837,6 +1839,7 @@ struct ieee80211_vif_cfg { u16 aid; u16 eml_cap; u16 eml_med_sync_delay; + u16 mld_capa_op; __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; int arp_addr_cnt; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 489dd97f5172..1e8da6372da2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4966,6 +4966,17 @@ static int ieee80211_set_hw_timestamp(struct wiphy *wiphy, return local->ops->set_hw_timestamp(&local->hw, &sdata->vif, hwts); } +static int +ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ttlm_params *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + lockdep_assert_wiphy(sdata->local->hw.wiphy); + + return ieee80211_req_neg_ttlm(sdata, params); +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -5078,4 +5089,5 @@ const struct cfg80211_ops mac80211_config_ops = { .mod_link_station = ieee80211_mod_link_station, .del_link_station = ieee80211_del_link_station, .set_hw_timestamp = ieee80211_set_hw_timestamp, + .set_ttlm = ieee80211_set_ttlm, }; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 38755f6f6fa0..79a5067ce82b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -579,6 +579,10 @@ struct ieee80211_if_managed { /* TID-to-link mapping support */ struct wiphy_delayed_work ttlm_work; struct ieee80211_adv_ttlm_info ttlm_info; + + /* dialog token enumerator for neg TTLM request */ + u8 dialog_token_alloc; + struct wiphy_delayed_work neg_ttlm_timeout_work; }; struct ieee80211_if_ibss { @@ -2605,6 +2609,10 @@ ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata, struct link_sta_info *link_sta); void ieee80211_process_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); +void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len); +int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata, + struct cfg80211_ttlm_params *params); void ieee80211_check_wbrf_support(struct ieee80211_local *local); void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4a87d2d336ae..df314222c2c9 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1554,6 +1554,10 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local, ieee80211_process_neg_ttlm_req(sdata, mgmt, skb->len); break; + case WLAN_PROTECTED_EHT_ACTION_TTLM_RES: + ieee80211_process_neg_ttlm_res(sdata, mgmt, + skb->len); + break; default: break; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b56f7de3b53f..5279af09fd53 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -46,6 +46,8 @@ #define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS msecs_to_jiffies(100) #define IEEE80211_ADV_TTLM_ST_UNDERFLOW 0xff00 +#define IEEE80211_NEG_TTLM_REQ_TIMEOUT (HZ / 5) + static int max_nullfunc_tries = 2; module_param(max_nullfunc_tries, int, 0644); MODULE_PARM_DESC(max_nullfunc_tries, @@ -3087,6 +3089,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(&sdata->u.mgd.ttlm_info, 0, sizeof(sdata->u.mgd.ttlm_info)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &ifmgd->neg_ttlm_timeout_work); ieee80211_vif_set_links(sdata, 0, 0); } @@ -4984,6 +4988,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ieee80211_mle_get_eml_cap(eht_ml_elem->data + 1); sdata->vif.cfg.eml_med_sync_delay = ieee80211_mle_get_eml_med_sync_delay(eht_ml_elem->data + 1); + sdata->vif.cfg.mld_capa_op = + ieee80211_mle_get_mld_capa_op(eht_ml_elem->data + 1); } } @@ -6501,6 +6507,19 @@ static void ieee80211_apply_neg_ttlm(struct ieee80211_sub_if_data *sdata, sdata->vif.neg_ttlm.valid = true; } +static void ieee80211_neg_ttlm_timeout_work(struct wiphy *wiphy, + struct wiphy_work *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.neg_ttlm_timeout_work.work); + + sdata_info(sdata, + "No negotiated TTLM response from AP, disconnecting.\n"); + + __ieee80211_disconnect(sdata); +} + static void ieee80211_neg_ttlm_add_suggested_map(struct sk_buff *skb, struct ieee80211_neg_ttlm *neg_ttlm) @@ -6547,6 +6566,74 @@ ieee80211_neg_ttlm_add_suggested_map(struct sk_buff *skb, } } +static void +ieee80211_send_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_neg_ttlm *neg_ttlm, + u8 dialog_token) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_req); + int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 + + 2 * 2 * IEEE80211_TTLM_NUM_TIDS; + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len); + if (!skb) + return; + + skb_reserve(skb, local->tx_headroom); + mgmt = skb_put_zero(skb, hdr_len); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT; + mgmt->u.action.u.ttlm_req.action_code = + WLAN_PROTECTED_EHT_ACTION_TTLM_REQ; + mgmt->u.action.u.ttlm_req.dialog_token = dialog_token; + ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm); + ieee80211_tx_skb(sdata, skb); +} + +int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata, + struct cfg80211_ttlm_params *params) +{ + struct ieee80211_neg_ttlm neg_ttlm = {}; + u8 i; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + !(sdata->vif.cfg.mld_capa_op & + IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP)) + return -EINVAL; + + for (i = 0; i < IEEE80211_TTLM_NUM_TIDS; i++) { + if ((params->dlink[i] & ~sdata->vif.valid_links) || + (params->ulink[i] & ~sdata->vif.valid_links)) + return -EINVAL; + + neg_ttlm.downlink[i] = params->dlink[i]; + neg_ttlm.uplink[i] = params->ulink[i]; + } + + if (drv_can_neg_ttlm(sdata->local, sdata, &neg_ttlm) != + NEG_TTLM_RES_ACCEPT) + return -EINVAL; + + ieee80211_apply_neg_ttlm(sdata, neg_ttlm); + sdata->u.mgd.dialog_token_alloc++; + ieee80211_send_neg_ttlm_req(sdata, &sdata->vif.neg_ttlm, + sdata->u.mgd.dialog_token_alloc); + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work); + wiphy_delayed_work_queue(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work, + IEEE80211_NEG_TTLM_REQ_TIMEOUT); + return 0; +} + static void ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, enum ieee80211_neg_ttlm_res ttlm_res, @@ -6740,6 +6827,29 @@ out: ieee80211_send_neg_ttlm_res(sdata, ttlm_res, dialog_token, &neg_ttlm); } +void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) +{ + if (!ieee80211_vif_is_mld(&sdata->vif) || + mgmt->u.action.u.ttlm_req.dialog_token != + sdata->u.mgd.dialog_token_alloc) + return; + + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work); + + /* MLD station sends a TID to link mapping request, mainly to handle + * BTM (BSS transition management) request, in which case it needs to + * restrict the active links set. + * In this case it's not expected that the MLD AP will reject the + * negotiated TTLM request. + * This can be better implemented in the future, to handle request + * rejections. + */ + if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS) + __ieee80211_disconnect(sdata); +} + void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -7369,6 +7479,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_sta_handle_tspec_ac_params_wk); wiphy_delayed_work_init(&ifmgd->ttlm_work, ieee80211_tid_to_link_map_work); + wiphy_delayed_work_init(&ifmgd->neg_ttlm_timeout_work, + ieee80211_neg_ttlm_timeout_work); ifmgd->flags = 0; ifmgd->powersave = sdata->wdev.ps; @@ -8459,6 +8571,8 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ml_reconf_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &ifmgd->neg_ttlm_timeout_work); if (ifmgd->assoc_data) ieee80211_destroy_assoc_data(sdata, ASSOC_TIMEOUT); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 75eb3e55eaec..615795c4b052 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3773,6 +3773,14 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) u.action.u.ttlm_req)) goto invalid; goto queue; + case WLAN_PROTECTED_EHT_ACTION_TTLM_RES: + if (sdata->vif.type != NL80211_IFTYPE_STATION) + break; + + if (len < offsetofend(typeof(*mgmt), + u.action.u.ttlm_res)) + goto invalid; + goto queue; default: break; } -- cgit v1.2.3 From ccb964b4ab1663ce92f389b72c052fc47a0ffdb9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 2 Jan 2024 21:35:44 +0200 Subject: wifi: cfg80211: validate MLO connections better When going into an MLO connection, validate that the link IDs match what userspace indicated, and that the AP MLD addresses and capabilities are all matching between the links. Signed-off-by: Johannes Berg Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20240102213313.ff83c034cb9a.I9962db0bfa8c73b37b8d5b59a3fad7f02f2129ae@changeid [roll in extra fix from Miri to actually check the return value] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 24 ++++++++ net/wireless/core.h | 3 +- net/wireless/mlme.c | 136 +++++++++++++++++++++++++++++++++++++++++----- net/wireless/nl80211.c | 3 +- net/wireless/sme.c | 3 +- 5 files changed, 152 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f0c068446c79..a70388ae3a7b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4935,6 +4935,30 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) return sizeof(*mle) + common + mle->variable[0]; } +/** + * ieee80211_mle_get_link_id - returns the link ID + * @data: the basic multi link element + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + * + * If the BSS link ID can't be found, -1 will be returned + */ +static inline int ieee80211_mle_get_link_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID)) + return -1; + + return *common; +} + /** * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count * @mle: the basic multi link element diff --git a/net/wireless/core.h b/net/wireless/core.h index 13657a85cf61..30434551b377 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -362,7 +362,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, struct cfg80211_auth_request *req); int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct cfg80211_assoc_request *req); + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack); int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, const u8 *ie, int ie_len, u16 reason, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 43ba7891e2a3..4052041a19ea 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -4,7 +4,7 @@ * * Copyright (c) 2009, Jouni Malinen * Copyright (c) 2015 Intel Deutschland GmbH - * Copyright (C) 2019-2020, 2022-2023 Intel Corporation + * Copyright (C) 2019-2020, 2022-2024 Intel Corporation */ #include @@ -325,28 +325,136 @@ void cfg80211_oper_and_vht_capa(struct ieee80211_vht_cap *vht_capa, p1[i] &= p2[i]; } -/* Note: caller must cfg80211_put_bss() regardless of result */ -int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_assoc_request *req) +static int +cfg80211_mlme_check_mlo_compat(const struct ieee80211_multi_link_elem *mle_a, + const struct ieee80211_multi_link_elem *mle_b, + struct netlink_ext_ack *extack) { - struct wireless_dev *wdev = dev->ieee80211_ptr; - int err, i, j; + const struct ieee80211_mle_basic_common_info *common_a, *common_b; - lockdep_assert_wiphy(wdev->wiphy); + common_a = (const void *)mle_a->variable; + common_b = (const void *)mle_b->variable; + + if (memcmp(common_a->mld_mac_addr, common_b->mld_mac_addr, ETH_ALEN)) { + NL_SET_ERR_MSG(extack, "AP MLD address mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_eml_med_sync_delay((const u8 *)mle_a) != + ieee80211_mle_get_eml_med_sync_delay((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link EML medium sync delay mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_eml_cap((const u8 *)mle_a) != + ieee80211_mle_get_eml_cap((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link EML capabilities mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_mld_capa_op((const u8 *)mle_a) != + ieee80211_mle_get_mld_capa_op((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link MLD capabilities/ops mismatch"); + return -EINVAL; + } + + return 0; +} + +static int cfg80211_mlme_check_mlo(struct net_device *dev, + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack) +{ + const struct ieee80211_multi_link_elem *mles[ARRAY_SIZE(req->links)] = {}; + int i; + + if (req->link_id < 0) + return 0; + + if (!req->links[req->link_id].bss) { + NL_SET_ERR_MSG(extack, "no BSS for assoc link"); + return -EINVAL; + } + + rcu_read_lock(); + for (i = 0; i < ARRAY_SIZE(req->links); i++) { + const struct cfg80211_bss_ies *ies; + const struct element *ml; - for (i = 1; i < ARRAY_SIZE(req->links); i++) { if (!req->links[i].bss) continue; - for (j = 0; j < i; j++) { - if (req->links[i].bss == req->links[j].bss) - return -EINVAL; + + if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr)) { + NL_SET_ERR_MSG(extack, "BSSID must not be our address"); + req->links[i].error = -EINVAL; + goto error; } - if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr)) - return -EINVAL; + ies = rcu_dereference(req->links[i].bss->ies); + ml = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK, + ies->data, ies->len); + if (!ml) { + NL_SET_ERR_MSG(extack, "MLO BSS w/o ML element"); + req->links[i].error = -EINVAL; + goto error; + } + + if (!ieee80211_mle_type_ok(ml->data + 1, + IEEE80211_ML_CONTROL_TYPE_BASIC, + ml->datalen - 1)) { + NL_SET_ERR_MSG(extack, "BSS with invalid ML element"); + req->links[i].error = -EINVAL; + goto error; + } + + mles[i] = (const void *)(ml->data + 1); + + if (ieee80211_mle_get_link_id((const u8 *)mles[i]) != i) { + NL_SET_ERR_MSG(extack, "link ID mismatch"); + req->links[i].error = -EINVAL; + goto error; + } + } + + if (WARN_ON(!mles[req->link_id])) + goto error; + + for (i = 0; i < ARRAY_SIZE(req->links); i++) { + if (i == req->link_id || !req->links[i].bss) + continue; + + if (WARN_ON(!mles[i])) + goto error; + + if (cfg80211_mlme_check_mlo_compat(mles[req->link_id], mles[i], + extack)) { + req->links[i].error = -EINVAL; + goto error; + } } + rcu_read_unlock(); + return 0; +error: + rcu_read_unlock(); + return -EINVAL; +} + +/* Note: caller must cfg80211_put_bss() regardless of result */ +int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + lockdep_assert_wiphy(wdev->wiphy); + + err = cfg80211_mlme_check_mlo(dev, req, extack); + if (err) + return err; + if (wdev->connected && (!req->prev_bssid || !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid))) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b267317aa33c..0809f721f045 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -11245,7 +11245,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct nlattr *link; int rem = 0; - err = cfg80211_mlme_assoc(rdev, dev, &req); + err = cfg80211_mlme_assoc(rdev, dev, &req, + info->extack); if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER]) { dev->ieee80211_ptr->conn_owner_nlportid = diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 195c8532734b..82e3ce42206c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -209,7 +209,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, if (!req.bss) { err = -ENOENT; } else { - err = cfg80211_mlme_assoc(rdev, wdev->netdev, &req); + err = cfg80211_mlme_assoc(rdev, wdev->netdev, + &req, NULL); cfg80211_put_bss(&rdev->wiphy, req.bss); } -- cgit v1.2.3 From 7ae215ee7bb855f13c80565470fc7f67db4ba82f Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Thu, 25 Jan 2024 21:36:59 +0100 Subject: net: phy: add support for PHY LEDs polarity modes Add support for PHY LEDs polarity modes. Some PHY require LED to be set to active low to be turned ON. Adds support for this by declaring active-low property in DT. PHY driver needs to declare .led_polarity_set() to configure LED polarity modes. Function will pass the index with the LED index and a bitmap with all the required modes to set. Current supported modes are: - active-low with the flag PHY_LED_ACTIVE_LOW. LED is set to active-low to turn it ON. - inactive-high-impedance with the flag PHY_LED_INACTIVE_HIGH_IMPEDANCE. LED is set to high impedance to turn it OFF. Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240125203702.4552-4-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 16 ++++++++++++++++ include/linux/phy.h | 22 ++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 3611ea64875e..dd778c7fde1d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3097,6 +3097,7 @@ static int of_phy_led(struct phy_device *phydev, struct device *dev = &phydev->mdio.dev; struct led_init_data init_data = {}; struct led_classdev *cdev; + unsigned long modes = 0; struct phy_led *phyled; u32 index; int err; @@ -3114,6 +3115,21 @@ static int of_phy_led(struct phy_device *phydev, if (index > U8_MAX) return -EINVAL; + if (of_property_read_bool(led, "active-low")) + set_bit(PHY_LED_ACTIVE_LOW, &modes); + if (of_property_read_bool(led, "inactive-high-impedance")) + set_bit(PHY_LED_INACTIVE_HIGH_IMPEDANCE, &modes); + + if (modes) { + /* Return error if asked to set polarity modes but not supported */ + if (!phydev->drv->led_polarity_set) + return -EINVAL; + + err = phydev->drv->led_polarity_set(phydev, index, modes); + if (err) + return err; + } + phyled->index = index; if (phydev->drv->led_brightness_set) cdev->brightness_set_blocking = phy_led_set_brightness; diff --git a/include/linux/phy.h b/include/linux/phy.h index 684efaeca07c..c9994a59ca2e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -852,6 +852,15 @@ struct phy_plca_status { bool pst; }; +/* Modes for PHY LED configuration */ +enum phy_led_modes { + PHY_LED_ACTIVE_LOW = 0, + PHY_LED_INACTIVE_HIGH_IMPEDANCE = 1, + + /* keep it last */ + __PHY_LED_MODES_NUM, +}; + /** * struct phy_led: An LED driven by the PHY * @@ -1145,6 +1154,19 @@ struct phy_driver { int (*led_hw_control_get)(struct phy_device *dev, u8 index, unsigned long *rules); + /** + * @led_polarity_set: Set the LED polarity modes + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @modes: bitmap of LED polarity modes + * + * Configure LED with all the required polarity modes in @modes + * to make it correctly turn ON or OFF. + * + * Returns 0, or an error code. + */ + int (*led_polarity_set)(struct phy_device *dev, int index, + unsigned long modes); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From ea1cc3ee34a5f3144f6c2cdc07c19c914ccb9526 Mon Sep 17 00:00:00 2001 From: Min Li Date: Wed, 24 Jan 2024 13:49:46 -0500 Subject: ptp: introduce PTP_CLOCK_EXTOFF event for the measured external offset This change is for the PHC devices that can measure the phase offset between PHC signal and the external signal, such as the 1PPS signal of GNSS. Reporting PTP_CLOCK_EXTOFF to user space will be piggy-backed to the existing ptp_extts_event so that application such as ts2phc can poll the external offset the same way as extts. Hence, ts2phc can use the offset to achieve the alignment between PHC and the external signal by the help of either SW or HW filters. Signed-off-by: Min Li Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 16 +++++++++++++++- include/linux/ptp_clock_kernel.h | 3 +++ include/uapi/linux/ptp_clock.h | 13 ++++++++++--- 3 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 15b804ba4868..3aaf1a3430c5 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -44,18 +44,31 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, struct ptp_clock_event *src) { struct ptp_extts_event *dst; + struct timespec64 offset_ts; unsigned long flags; s64 seconds; u32 remainder; - seconds = div_u64_rem(src->timestamp, 1000000000, &remainder); + if (src->type == PTP_CLOCK_EXTTS) { + seconds = div_u64_rem(src->timestamp, 1000000000, &remainder); + } else if (src->type == PTP_CLOCK_EXTOFF) { + offset_ts = ns_to_timespec64(src->offset); + seconds = offset_ts.tv_sec; + remainder = offset_ts.tv_nsec; + } else { + WARN(1, "%s: unknown type %d\n", __func__, src->type); + return; + } spin_lock_irqsave(&queue->lock, flags); dst = &queue->buf[queue->tail]; dst->index = src->index; + dst->flags = PTP_EXTTS_EVENT_VALID; dst->t.sec = seconds; dst->t.nsec = remainder; + if (src->type == PTP_CLOCK_EXTOFF) + dst->flags |= PTP_EXT_OFFSET; /* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */ if (!queue_free(queue)) @@ -417,6 +430,7 @@ void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event) break; case PTP_CLOCK_EXTTS: + case PTP_CLOCK_EXTOFF: /* Enqueue timestamp on selected queues */ spin_lock_irqsave(&ptp->tsevqs_lock, flags); list_for_each_entry(tsevq, &ptp->tsevqs, qlist) { diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 1ef4e0f9bd2a..6e4b8206c7d0 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -200,6 +200,7 @@ struct ptp_clock; enum ptp_clock_events { PTP_CLOCK_ALARM, PTP_CLOCK_EXTTS, + PTP_CLOCK_EXTOFF, PTP_CLOCK_PPS, PTP_CLOCK_PPSUSR, }; @@ -210,6 +211,7 @@ enum ptp_clock_events { * @type: One of the ptp_clock_events enumeration values. * @index: Identifies the source of the event. * @timestamp: When the event occurred (%PTP_CLOCK_EXTTS only). + * @offset: When the event occurred (%PTP_CLOCK_EXTOFF only). * @pps_times: When the event occurred (%PTP_CLOCK_PPSUSR only). */ @@ -218,6 +220,7 @@ struct ptp_clock_event { int index; union { u64 timestamp; + s64 offset; struct pps_event_time pps_times; }; }; diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index da700999cad4..053b40d642de 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -32,6 +32,7 @@ #define PTP_RISING_EDGE (1<<1) #define PTP_FALLING_EDGE (1<<2) #define PTP_STRICT_FLAGS (1<<3) +#define PTP_EXT_OFFSET (1<<4) #define PTP_EXTTS_EDGES (PTP_RISING_EDGE | PTP_FALLING_EDGE) /* @@ -40,7 +41,8 @@ #define PTP_EXTTS_VALID_FLAGS (PTP_ENABLE_FEATURE | \ PTP_RISING_EDGE | \ PTP_FALLING_EDGE | \ - PTP_STRICT_FLAGS) + PTP_STRICT_FLAGS | \ + PTP_EXT_OFFSET) /* * flag fields valid for the original PTP_EXTTS_REQUEST ioctl. @@ -50,6 +52,11 @@ PTP_RISING_EDGE | \ PTP_FALLING_EDGE) +/* + * flag fields valid for the ptp_extts_event report. + */ +#define PTP_EXTTS_EVENT_VALID (PTP_ENABLE_FEATURE) + /* * Bits of the ptp_perout_request.flags field: */ @@ -228,9 +235,9 @@ struct ptp_pin_desc { #define PTP_MASK_EN_SINGLE _IOW(PTP_CLK_MAGIC, 20, unsigned int) struct ptp_extts_event { - struct ptp_clock_time t; /* Time event occured. */ + struct ptp_clock_time t; /* Time event occurred. */ unsigned int index; /* Which channel produced the event. */ - unsigned int flags; /* Reserved for future use. */ + unsigned int flags; /* Event type. */ unsigned int rsv[2]; /* Reserved for future use. */ }; -- cgit v1.2.3 From 1ddfecafabf71e0e5345dff877d2680083c7e078 Mon Sep 17 00:00:00 2001 From: Min Li Date: Wed, 24 Jan 2024 13:49:47 -0500 Subject: ptp: add FemtoClock3 Wireless as ptp hardware clock The RENESAS FemtoClock3 Wireless is a high-performance jitter attenuator, frequency translator, and clock synthesizer. The device is comprised of 3 digital PLLs (DPLL) to track CLKIN inputs and three independent low phase noise fractional output dividers (FOD) that output low phase noise clocks. FemtoClock3 supports one Time Synchronization (Time Sync) channel to enable an external processor to control the phase and frequency of the Time Sync channel and to take phase measurements using the TDC. Intended applications are synchronization using the precision time protocol (PTP) and synchronization with 0.5 Hz and 1 Hz signals from GNSS. Signed-off-by: Min Li Acked-by: Lee Jones Signed-off-by: David S. Miller --- drivers/ptp/Kconfig | 12 + drivers/ptp/Makefile | 1 + drivers/ptp/ptp_fc3.c | 1016 ++++++++++++++++++++++++++++++++++++ drivers/ptp/ptp_fc3.h | 45 ++ include/linux/mfd/idtRC38xxx_reg.h | 273 ++++++++++ 5 files changed, 1347 insertions(+) create mode 100644 drivers/ptp/ptp_fc3.c create mode 100644 drivers/ptp/ptp_fc3.h create mode 100644 include/linux/mfd/idtRC38xxx_reg.h (limited to 'include/linux') diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 5dd5f188e14f..604541dcb320 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -155,6 +155,18 @@ config PTP_1588_CLOCK_IDTCM To compile this driver as a module, choose M here: the module will be called ptp_clockmatrix. +config PTP_1588_CLOCK_FC3W + tristate "RENESAS FemtoClock3 Wireless as PTP clock" + depends on PTP_1588_CLOCK && I2C + default n + help + This driver adds support for using Renesas FemtoClock3 Wireless + as a PTP clock. This clock is only useful if your time stamping + MAC is connected to the RENESAS chip. + + To compile this driver as a module, choose M here: the module + will be called ptp_fc3. + config PTP_1588_CLOCK_MOCK tristate "Mock-up PTP clock" depends on PTP_1588_CLOCK diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index dea0cebd2303..68bf02078053 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp-qoriq.o ptp-qoriq-y += ptp_qoriq.o ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o +obj-$(CONFIG_PTP_1588_CLOCK_FC3W) += ptp_fc3.o obj-$(CONFIG_PTP_1588_CLOCK_IDT82P33) += ptp_idt82p33.o obj-$(CONFIG_PTP_1588_CLOCK_MOCK) += ptp_mock.o obj-$(CONFIG_PTP_1588_CLOCK_VMW) += ptp_vmw.o diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c new file mode 100644 index 000000000000..0e2286ba088a --- /dev/null +++ b/drivers/ptp/ptp_fc3.c @@ -0,0 +1,1016 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PTP hardware clock driver for the FemtoClock3 family of timing and + * synchronization devices. + * + * Copyright (C) 2023 Integrated Device Technology, Inc., a Renesas Company. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ptp_private.h" +#include "ptp_fc3.h" + +MODULE_DESCRIPTION("Driver for IDT FemtoClock3(TM) family"); +MODULE_AUTHOR("IDT support-1588 "); +MODULE_VERSION("1.0"); +MODULE_LICENSE("GPL"); + +/* + * The name of the firmware file to be loaded + * over-rides any automatic selection + */ +static char *firmware; +module_param(firmware, charp, 0); + +static s64 ns2counters(struct idtfc3 *idtfc3, s64 nsec, u32 *sub_ns) +{ + s64 sync; + s32 rem; + + if (likely(nsec >= 0)) { + sync = div_u64_rem(nsec, idtfc3->ns_per_sync, &rem); + *sub_ns = rem; + } else { + sync = -div_u64_rem(-nsec - 1, idtfc3->ns_per_sync, &rem) - 1; + *sub_ns = idtfc3->ns_per_sync - rem - 1; + } + + return sync * idtfc3->ns_per_sync; +} + +static s64 tdc_meas2offset(struct idtfc3 *idtfc3, u64 meas_read) +{ + s64 coarse, fine; + + fine = sign_extend64(FIELD_GET(FINE_MEAS_MASK, meas_read), 12); + coarse = sign_extend64(FIELD_GET(COARSE_MEAS_MASK, meas_read), (39 - 13)); + + fine = div64_s64(fine * NSEC_PER_SEC, idtfc3->tdc_apll_freq * 62LL); + coarse = div64_s64(coarse * NSEC_PER_SEC, idtfc3->time_ref_freq); + + return coarse + fine; +} + +static s64 tdc_offset2phase(struct idtfc3 *idtfc3, s64 offset_ns) +{ + if (offset_ns > idtfc3->ns_per_sync / 2) + offset_ns -= idtfc3->ns_per_sync; + + return offset_ns * idtfc3->tdc_offset_sign; +} + +static int idtfc3_set_lpf_mode(struct idtfc3 *idtfc3, u8 mode) +{ + int err; + + if (mode >= LPF_INVALID) + return -EINVAL; + + if (idtfc3->lpf_mode == mode) + return 0; + + err = regmap_bulk_write(idtfc3->regmap, LPF_MODE_CNFG, &mode, sizeof(mode)); + if (err) + return err; + + idtfc3->lpf_mode = mode; + + return 0; +} + +static int idtfc3_enable_lpf(struct idtfc3 *idtfc3, bool enable) +{ + u8 val; + int err; + + err = regmap_bulk_read(idtfc3->regmap, LPF_CTRL, &val, sizeof(val)); + if (err) + return err; + + if (enable == true) + val |= LPF_EN; + else + val &= ~LPF_EN; + + return regmap_bulk_write(idtfc3->regmap, LPF_CTRL, &val, sizeof(val)); +} + +static int idtfc3_get_time_ref_freq(struct idtfc3 *idtfc3) +{ + int err; + u8 buf[4]; + u8 time_ref_div; + u8 time_clk_div; + + err = regmap_bulk_read(idtfc3->regmap, TIME_CLOCK_MEAS_DIV_CNFG, buf, sizeof(buf)); + if (err) + return err; + time_ref_div = FIELD_GET(TIME_REF_DIV_MASK, get_unaligned_le32(buf)) + 1; + + err = regmap_bulk_read(idtfc3->regmap, TIME_CLOCK_COUNT, buf, 1); + if (err) + return err; + time_clk_div = (buf[0] & TIME_CLOCK_COUNT_MASK) + 1; + idtfc3->time_ref_freq = idtfc3->hw_param.time_clk_freq * + time_clk_div / time_ref_div; + + return 0; +} + +static int idtfc3_get_tdc_offset_sign(struct idtfc3 *idtfc3) +{ + int err; + u8 buf[4]; + u32 val; + u8 sig1, sig2; + + err = regmap_bulk_read(idtfc3->regmap, TIME_CLOCK_TDC_FANOUT_CNFG, buf, sizeof(buf)); + if (err) + return err; + + val = get_unaligned_le32(buf); + if ((val & TIME_SYNC_TO_TDC_EN) != TIME_SYNC_TO_TDC_EN) { + dev_err(idtfc3->dev, "TIME_SYNC_TO_TDC_EN is off !!!"); + return -EINVAL; + } + + sig1 = FIELD_GET(SIG1_MUX_SEL_MASK, val); + sig2 = FIELD_GET(SIG2_MUX_SEL_MASK, val); + + if ((sig1 == sig2) || ((sig1 != TIME_SYNC) && (sig2 != TIME_SYNC))) { + dev_err(idtfc3->dev, "Invalid tdc_mux_sel sig1=%d sig2=%d", sig1, sig2); + return -EINVAL; + } else if (sig1 == TIME_SYNC) { + idtfc3->tdc_offset_sign = 1; + } else if (sig2 == TIME_SYNC) { + idtfc3->tdc_offset_sign = -1; + } + + return 0; +} + +static int idtfc3_lpf_bw(struct idtfc3 *idtfc3, u8 shift, u8 mult) +{ + u8 val = FIELD_PREP(LPF_BW_SHIFT, shift) | FIELD_PREP(LPF_BW_MULT, mult); + + return regmap_bulk_write(idtfc3->regmap, LPF_BW_CNFG, &val, sizeof(val)); +} + +static int idtfc3_enable_tdc(struct idtfc3 *idtfc3, bool enable, u8 meas_mode) +{ + int err; + u8 val = 0; + + /* Disable TDC first */ + err = regmap_bulk_write(idtfc3->regmap, TIME_CLOCK_MEAS_CTRL, &val, sizeof(val)); + if (err) + return err; + + if (enable == false) + return idtfc3_lpf_bw(idtfc3, LPF_BW_SHIFT_DEFAULT, LPF_BW_MULT_DEFAULT); + + if (meas_mode >= MEAS_MODE_INVALID) + return -EINVAL; + + /* Change TDC meas mode */ + err = regmap_bulk_write(idtfc3->regmap, TIME_CLOCK_MEAS_CNFG, + &meas_mode, sizeof(meas_mode)); + if (err) + return err; + + /* Enable TDC */ + val = TDC_MEAS_EN; + if (meas_mode == CONTINUOUS) + val |= TDC_MEAS_START; + err = regmap_bulk_write(idtfc3->regmap, TIME_CLOCK_MEAS_CTRL, &val, sizeof(val)); + if (err) + return err; + + return idtfc3_lpf_bw(idtfc3, LPF_BW_SHIFT_1PPS, LPF_BW_MULT_DEFAULT); +} + +static bool get_tdc_meas(struct idtfc3 *idtfc3, s64 *offset_ns) +{ + bool valid = false; + u8 buf[9]; + u8 val; + int err; + + while (true) { + err = regmap_bulk_read(idtfc3->regmap, TDC_FIFO_STS, + &val, sizeof(val)); + if (err) + return false; + + if (val & FIFO_EMPTY) + break; + + err = regmap_bulk_read(idtfc3->regmap, TDC_FIFO_READ_REQ, + &buf, sizeof(buf)); + if (err) + return false; + + valid = true; + } + + if (valid) + *offset_ns = tdc_meas2offset(idtfc3, get_unaligned_le64(&buf[1])); + + return valid; +} + +static int check_tdc_fifo_overrun(struct idtfc3 *idtfc3) +{ + u8 val; + int err; + + /* Check if FIFO is overrun */ + err = regmap_bulk_read(idtfc3->regmap, TDC_FIFO_STS, &val, sizeof(val)); + if (err) + return err; + + if (!(val & FIFO_FULL)) + return 0; + + dev_warn(idtfc3->dev, "TDC FIFO overrun !!!"); + + err = idtfc3_enable_tdc(idtfc3, true, CONTINUOUS); + if (err) + return err; + + return 0; +} + +static int get_tdc_meas_continuous(struct idtfc3 *idtfc3) +{ + int err; + s64 offset_ns; + struct ptp_clock_event event; + + err = check_tdc_fifo_overrun(idtfc3); + if (err) + return err; + + if (get_tdc_meas(idtfc3, &offset_ns) && offset_ns >= 0) { + event.index = 0; + event.offset = tdc_offset2phase(idtfc3, offset_ns); + event.type = PTP_CLOCK_EXTOFF; + ptp_clock_event(idtfc3->ptp_clock, &event); + } + + return 0; +} + +static int idtfc3_read_subcounter(struct idtfc3 *idtfc3) +{ + u8 buf[5] = {0}; + int err; + + err = regmap_bulk_read(idtfc3->regmap, TOD_COUNTER_READ_REQ, + &buf, sizeof(buf)); + if (err) + return err; + + /* sync_counter_value is [31:82] and sub_sync_counter_value is [0:30] */ + return get_unaligned_le32(&buf[1]) & SUB_SYNC_COUNTER_MASK; +} + +static int idtfc3_tod_update_is_done(struct idtfc3 *idtfc3) +{ + int err; + u8 req; + + err = read_poll_timeout_atomic(regmap_bulk_read, err, !req, USEC_PER_MSEC, + idtfc3->tc_write_timeout, true, idtfc3->regmap, + TOD_SYNC_LOAD_REQ_CTRL, &req, 1); + if (err) + dev_err(idtfc3->dev, "TOD counter write timeout !!!"); + + return err; +} + +static int idtfc3_write_subcounter(struct idtfc3 *idtfc3, u32 counter) +{ + u8 buf[18] = {0}; + int err; + + /* sync_counter_value is [31:82] and sub_sync_counter_value is [0:30] */ + put_unaligned_le32(counter & SUB_SYNC_COUNTER_MASK, &buf[0]); + + buf[16] = SUB_SYNC_LOAD_ENABLE | SYNC_LOAD_ENABLE; + buf[17] = SYNC_LOAD_REQ; + + err = regmap_bulk_write(idtfc3->regmap, TOD_SYNC_LOAD_VAL_CTRL, + &buf, sizeof(buf)); + if (err) + return err; + + return idtfc3_tod_update_is_done(idtfc3); +} + +static int idtfc3_timecounter_update(struct idtfc3 *idtfc3, u32 counter, s64 ns) +{ + int err; + + err = idtfc3_write_subcounter(idtfc3, counter); + if (err) + return err; + + /* Update time counter */ + idtfc3->ns = ns; + idtfc3->last_counter = counter; + + return 0; +} + +static int idtfc3_timecounter_read(struct idtfc3 *idtfc3) +{ + int now, delta; + + now = idtfc3_read_subcounter(idtfc3); + if (now < 0) + return now; + + /* calculate the delta since the last idtfc3_timecounter_read(): */ + if (now >= idtfc3->last_counter) + delta = now - idtfc3->last_counter; + else + delta = idtfc3->sub_sync_count - idtfc3->last_counter + now; + + /* Update time counter */ + idtfc3->ns += delta * idtfc3->ns_per_counter; + idtfc3->last_counter = now; + + return 0; +} + +static int _idtfc3_gettime(struct idtfc3 *idtfc3, struct timespec64 *ts) +{ + int err; + + err = idtfc3_timecounter_read(idtfc3); + if (err) + return err; + + *ts = ns_to_timespec64(idtfc3->ns); + + return 0; +} + +static int idtfc3_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err; + + mutex_lock(idtfc3->lock); + err = _idtfc3_gettime(idtfc3, ts); + mutex_unlock(idtfc3->lock); + + return err; +} + +static int _idtfc3_settime(struct idtfc3 *idtfc3, const struct timespec64 *ts) +{ + s64 offset_ns, now_ns; + u32 counter, sub_ns; + int now; + + if (timespec64_valid(ts) == false) { + dev_err(idtfc3->dev, "%s: invalid timespec", __func__); + return -EINVAL; + } + + now = idtfc3_read_subcounter(idtfc3); + if (now < 0) + return now; + + offset_ns = (idtfc3->sub_sync_count - now) * idtfc3->ns_per_counter; + now_ns = timespec64_to_ns(ts); + (void)ns2counters(idtfc3, offset_ns + now_ns, &sub_ns); + + counter = sub_ns / idtfc3->ns_per_counter; + return idtfc3_timecounter_update(idtfc3, counter, now_ns); +} + +static int idtfc3_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err; + + mutex_lock(idtfc3->lock); + err = _idtfc3_settime(idtfc3, ts); + mutex_unlock(idtfc3->lock); + + return err; +} + +static int _idtfc3_adjtime(struct idtfc3 *idtfc3, s64 delta) +{ + /* + * The TOD counter can be synchronously loaded with any value, + * to be loaded on the next Time Sync pulse + */ + s64 sync_ns; + u32 sub_ns; + u32 counter; + + if (idtfc3->ns + delta < 0) { + dev_err(idtfc3->dev, "%lld ns adj is too large", delta); + return -EINVAL; + } + + sync_ns = ns2counters(idtfc3, delta + idtfc3->ns_per_sync, &sub_ns); + + counter = sub_ns / idtfc3->ns_per_counter; + return idtfc3_timecounter_update(idtfc3, counter, idtfc3->ns + sync_ns + + counter * idtfc3->ns_per_counter); +} + +static int idtfc3_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err; + + mutex_lock(idtfc3->lock); + err = _idtfc3_adjtime(idtfc3, delta); + mutex_unlock(idtfc3->lock); + + return err; +} + +static int _idtfc3_adjphase(struct idtfc3 *idtfc3, s32 delta) +{ + u8 buf[8] = {0}; + int err; + s64 pcw; + + err = idtfc3_set_lpf_mode(idtfc3, LPF_WP); + if (err) + return err; + + /* + * Phase Control Word unit is: 10^9 / (TDC_APLL_FREQ * 124) + * + * delta * TDC_APLL_FREQ * 124 + * PCW = --------------------------- + * 10^9 + * + */ + pcw = div_s64((s64)delta * idtfc3->tdc_apll_freq * 124, NSEC_PER_SEC); + + put_unaligned_le64(pcw, buf); + + return regmap_bulk_write(idtfc3->regmap, LPF_WR_PHASE_CTRL, buf, sizeof(buf)); +} + +static int idtfc3_adjphase(struct ptp_clock_info *ptp, s32 delta) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err; + + mutex_lock(idtfc3->lock); + err = _idtfc3_adjphase(idtfc3, delta); + mutex_unlock(idtfc3->lock); + + return err; +} + +static int _idtfc3_adjfine(struct idtfc3 *idtfc3, long scaled_ppm) +{ + u8 buf[8] = {0}; + int err; + s64 fcw; + + err = idtfc3_set_lpf_mode(idtfc3, LPF_WF); + if (err) + return err; + + /* + * Frequency Control Word unit is: 2^-44 * 10^6 ppm + * + * adjfreq: + * ppb * 2^44 + * FCW = ---------- + * 10^9 + * + * adjfine: + * ppm_16 * 2^28 + * FCW = ------------- + * 10^6 + */ + fcw = scaled_ppm * BIT(28); + fcw = div_s64(fcw, 1000000); + + put_unaligned_le64(fcw, buf); + + return regmap_bulk_write(idtfc3->regmap, LPF_WR_FREQ_CTRL, buf, sizeof(buf)); +} + +static int idtfc3_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err; + + mutex_lock(idtfc3->lock); + err = _idtfc3_adjfine(idtfc3, scaled_ppm); + mutex_unlock(idtfc3->lock); + + return err; +} + +static int idtfc3_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + int err = -EOPNOTSUPP; + + mutex_lock(idtfc3->lock); + switch (rq->type) { + case PTP_CLK_REQ_PEROUT: + if (!on) + err = 0; + /* Only accept a 1-PPS aligned to the second. */ + else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || + rq->perout.period.nsec) + err = -ERANGE; + else + err = 0; + break; + case PTP_CLK_REQ_EXTTS: + if (on) { + /* Only accept requests for external phase offset */ + if ((rq->extts.flags & PTP_EXT_OFFSET) != (PTP_EXT_OFFSET)) + err = -EOPNOTSUPP; + else + err = idtfc3_enable_tdc(idtfc3, true, CONTINUOUS); + } else { + err = idtfc3_enable_tdc(idtfc3, false, MEAS_MODE_INVALID); + } + break; + default: + break; + } + mutex_unlock(idtfc3->lock); + + if (err) + dev_err(idtfc3->dev, "Failed in %s with err %d!", __func__, err); + + return err; +} + +static long idtfc3_aux_work(struct ptp_clock_info *ptp) +{ + struct idtfc3 *idtfc3 = container_of(ptp, struct idtfc3, caps); + static int tdc_get; + + mutex_lock(idtfc3->lock); + tdc_get %= TDC_GET_PERIOD; + if ((tdc_get == 0) || (tdc_get == TDC_GET_PERIOD / 2)) + idtfc3_timecounter_read(idtfc3); + get_tdc_meas_continuous(idtfc3); + tdc_get++; + mutex_unlock(idtfc3->lock); + + return idtfc3->tc_update_period; +} + +static const struct ptp_clock_info idtfc3_caps = { + .owner = THIS_MODULE, + .max_adj = MAX_FFO_PPB, + .n_per_out = 1, + .n_ext_ts = 1, + .adjphase = &idtfc3_adjphase, + .adjfine = &idtfc3_adjfine, + .adjtime = &idtfc3_adjtime, + .gettime64 = &idtfc3_gettime, + .settime64 = &idtfc3_settime, + .enable = &idtfc3_enable, + .do_aux_work = &idtfc3_aux_work, +}; + +static int idtfc3_hw_calibrate(struct idtfc3 *idtfc3) +{ + int err = 0; + u8 val; + + mdelay(10); + /* + * Toggle TDC_DAC_RECAL_REQ: + * (1) set tdc_en to 1 + * (2) set tdc_dac_recal_req to 0 + * (3) set tdc_dac_recal_req to 1 + */ + val = TDC_EN; + err = regmap_bulk_write(idtfc3->regmap, TDC_CTRL, + &val, sizeof(val)); + if (err) + return err; + val = TDC_EN | TDC_DAC_RECAL_REQ; + err = regmap_bulk_write(idtfc3->regmap, TDC_CTRL, + &val, sizeof(val)); + if (err) + return err; + mdelay(10); + + /* + * Toggle APLL_REINIT: + * (1) set apll_reinit to 0 + * (2) set apll_reinit to 1 + */ + val = 0; + err = regmap_bulk_write(idtfc3->regmap, SOFT_RESET_CTRL, + &val, sizeof(val)); + if (err) + return err; + val = APLL_REINIT; + err = regmap_bulk_write(idtfc3->regmap, SOFT_RESET_CTRL, + &val, sizeof(val)); + if (err) + return err; + mdelay(10); + + return err; +} + +static int idtfc3_init_timecounter(struct idtfc3 *idtfc3) +{ + int err; + u32 period_ms; + + period_ms = idtfc3->sub_sync_count * MSEC_PER_SEC / + idtfc3->hw_param.time_clk_freq; + + idtfc3->tc_update_period = msecs_to_jiffies(period_ms / TDC_GET_PERIOD); + idtfc3->tc_write_timeout = period_ms * USEC_PER_MSEC; + + err = idtfc3_timecounter_update(idtfc3, 0, 0); + if (err) + return err; + + err = idtfc3_timecounter_read(idtfc3); + if (err) + return err; + + ptp_schedule_worker(idtfc3->ptp_clock, idtfc3->tc_update_period); + + return 0; +} + +static int idtfc3_get_tdc_apll_freq(struct idtfc3 *idtfc3) +{ + int err; + u8 tdc_fb_div_int; + u8 tdc_ref_div; + struct idtfc3_hw_param *param = &idtfc3->hw_param; + + err = regmap_bulk_read(idtfc3->regmap, TDC_REF_DIV_CNFG, + &tdc_ref_div, sizeof(tdc_ref_div)); + if (err) + return err; + + err = regmap_bulk_read(idtfc3->regmap, TDC_FB_DIV_INT_CNFG, + &tdc_fb_div_int, sizeof(tdc_fb_div_int)); + if (err) + return err; + + tdc_fb_div_int &= TDC_FB_DIV_INT_MASK; + tdc_ref_div &= TDC_REF_DIV_CONFIG_MASK; + + idtfc3->tdc_apll_freq = div_u64(param->xtal_freq * (u64)tdc_fb_div_int, + 1 << tdc_ref_div); + + return 0; +} + +static int idtfc3_get_fod(struct idtfc3 *idtfc3) +{ + int err; + u8 fod; + + err = regmap_bulk_read(idtfc3->regmap, TIME_CLOCK_SRC, &fod, sizeof(fod)); + if (err) + return err; + + switch (fod) { + case 0: + idtfc3->fod_n = FOD_0; + break; + case 1: + idtfc3->fod_n = FOD_1; + break; + case 2: + idtfc3->fod_n = FOD_2; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int idtfc3_get_sync_count(struct idtfc3 *idtfc3) +{ + int err; + u8 buf[4]; + + err = regmap_bulk_read(idtfc3->regmap, SUB_SYNC_GEN_CNFG, buf, sizeof(buf)); + if (err) + return err; + + idtfc3->sub_sync_count = (get_unaligned_le32(buf) & SUB_SYNC_COUNTER_MASK) + 1; + idtfc3->ns_per_counter = NSEC_PER_SEC / idtfc3->hw_param.time_clk_freq; + idtfc3->ns_per_sync = idtfc3->sub_sync_count * idtfc3->ns_per_counter; + + return 0; +} + +static int idtfc3_setup_hw_param(struct idtfc3 *idtfc3) +{ + int err; + + err = idtfc3_get_fod(idtfc3); + if (err) + return err; + + err = idtfc3_get_sync_count(idtfc3); + if (err) + return err; + + err = idtfc3_get_time_ref_freq(idtfc3); + if (err) + return err; + + return idtfc3_get_tdc_apll_freq(idtfc3); +} + +static int idtfc3_configure_hw(struct idtfc3 *idtfc3) +{ + int err = 0; + + err = idtfc3_hw_calibrate(idtfc3); + if (err) + return err; + + err = idtfc3_enable_lpf(idtfc3, true); + if (err) + return err; + + err = idtfc3_enable_tdc(idtfc3, false, MEAS_MODE_INVALID); + if (err) + return err; + + err = idtfc3_get_tdc_offset_sign(idtfc3); + if (err) + return err; + + return idtfc3_setup_hw_param(idtfc3); +} + +static int idtfc3_set_overhead(struct idtfc3 *idtfc3) +{ + s64 current_ns = 0; + s64 lowest_ns = 0; + int err; + u8 i; + ktime_t start; + ktime_t stop; + ktime_t diff; + + char buf[18] = {0}; + + for (i = 0; i < 5; i++) { + start = ktime_get_raw(); + + err = regmap_bulk_write(idtfc3->regmap, TOD_SYNC_LOAD_VAL_CTRL, + &buf, sizeof(buf)); + if (err) + return err; + + stop = ktime_get_raw(); + + diff = ktime_sub(stop, start); + + current_ns = ktime_to_ns(diff); + + if (i == 0) { + lowest_ns = current_ns; + } else { + if (current_ns < lowest_ns) + lowest_ns = current_ns; + } + } + + idtfc3->tod_write_overhead = lowest_ns; + + return err; +} + +static int idtfc3_enable_ptp(struct idtfc3 *idtfc3) +{ + int err; + + idtfc3->caps = idtfc3_caps; + snprintf(idtfc3->caps.name, sizeof(idtfc3->caps.name), "IDT FC3W"); + idtfc3->ptp_clock = ptp_clock_register(&idtfc3->caps, NULL); + + if (IS_ERR(idtfc3->ptp_clock)) { + err = PTR_ERR(idtfc3->ptp_clock); + idtfc3->ptp_clock = NULL; + return err; + } + + err = idtfc3_set_overhead(idtfc3); + if (err) + return err; + + err = idtfc3_init_timecounter(idtfc3); + if (err) + return err; + + dev_info(idtfc3->dev, "TIME_SYNC_CHANNEL registered as ptp%d", + idtfc3->ptp_clock->index); + + return 0; +} + +static int idtfc3_load_firmware(struct idtfc3 *idtfc3) +{ + char fname[128] = FW_FILENAME; + const struct firmware *fw; + struct idtfc3_fwrc *rec; + u16 addr; + u8 val; + int err; + s32 len; + + idtfc3_default_hw_param(&idtfc3->hw_param); + + if (firmware) /* module parameter */ + snprintf(fname, sizeof(fname), "%s", firmware); + + dev_info(idtfc3->dev, "requesting firmware '%s'\n", fname); + + err = request_firmware(&fw, fname, idtfc3->dev); + + if (err) { + dev_err(idtfc3->dev, + "requesting firmware failed with err %d!\n", err); + return err; + } + + dev_dbg(idtfc3->dev, "firmware size %zu bytes\n", fw->size); + + rec = (struct idtfc3_fwrc *)fw->data; + + for (len = fw->size; len > 0; len -= sizeof(*rec)) { + if (rec->reserved) { + dev_err(idtfc3->dev, + "bad firmware, reserved field non-zero\n"); + err = -EINVAL; + } else { + val = rec->value; + addr = rec->hiaddr << 8 | rec->loaddr; + + rec++; + + err = idtfc3_set_hw_param(&idtfc3->hw_param, addr, val); + } + + if (err != -EINVAL) { + err = 0; + + /* Max register */ + if (addr >= 0xE88) + continue; + + err = regmap_bulk_write(idtfc3->regmap, addr, + &val, sizeof(val)); + } + + if (err) + goto out; + } + + err = idtfc3_configure_hw(idtfc3); +out: + release_firmware(fw); + return err; +} + +static int idtfc3_read_device_id(struct idtfc3 *idtfc3, u16 *device_id) +{ + int err; + u8 buf[2] = {0}; + + err = regmap_bulk_read(idtfc3->regmap, DEVICE_ID, + &buf, sizeof(buf)); + if (err) { + dev_err(idtfc3->dev, "%s failed with %d", __func__, err); + return err; + } + + *device_id = get_unaligned_le16(buf); + + return 0; +} + +static int idtfc3_check_device_compatibility(struct idtfc3 *idtfc3) +{ + int err; + u16 device_id; + + err = idtfc3_read_device_id(idtfc3, &device_id); + if (err) + return err; + + if ((device_id & DEVICE_ID_MASK) == 0) { + dev_err(idtfc3->dev, "invalid device"); + return -EINVAL; + } + + return 0; +} + +static int idtfc3_probe(struct platform_device *pdev) +{ + struct rsmu_ddata *ddata = dev_get_drvdata(pdev->dev.parent); + struct idtfc3 *idtfc3; + int err; + + idtfc3 = devm_kzalloc(&pdev->dev, sizeof(struct idtfc3), GFP_KERNEL); + + if (!idtfc3) + return -ENOMEM; + + idtfc3->dev = &pdev->dev; + idtfc3->mfd = pdev->dev.parent; + idtfc3->lock = &ddata->lock; + idtfc3->regmap = ddata->regmap; + + mutex_lock(idtfc3->lock); + + err = idtfc3_check_device_compatibility(idtfc3); + if (err) { + mutex_unlock(idtfc3->lock); + return err; + } + + err = idtfc3_load_firmware(idtfc3); + if (err) { + if (err == -ENOENT) { + mutex_unlock(idtfc3->lock); + return -EPROBE_DEFER; + } + dev_warn(idtfc3->dev, "loading firmware failed with %d", err); + } + + err = idtfc3_enable_ptp(idtfc3); + if (err) { + dev_err(idtfc3->dev, "idtfc3_enable_ptp failed with %d", err); + mutex_unlock(idtfc3->lock); + return err; + } + + mutex_unlock(idtfc3->lock); + + if (err) { + ptp_clock_unregister(idtfc3->ptp_clock); + return err; + } + + platform_set_drvdata(pdev, idtfc3); + + return 0; +} + +static int idtfc3_remove(struct platform_device *pdev) +{ + struct idtfc3 *idtfc3 = platform_get_drvdata(pdev); + + ptp_clock_unregister(idtfc3->ptp_clock); + + return 0; +} + +static struct platform_driver idtfc3_driver = { + .driver = { + .name = "rc38xxx-phc", + }, + .probe = idtfc3_probe, + .remove = idtfc3_remove, +}; + +module_platform_driver(idtfc3_driver); diff --git a/drivers/ptp/ptp_fc3.h b/drivers/ptp/ptp_fc3.h new file mode 100644 index 000000000000..897101579207 --- /dev/null +++ b/drivers/ptp/ptp_fc3.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * PTP hardware clock driver for the FemtoClock3 family of timing and + * synchronization devices. + * + * Copyright (C) 2023 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef PTP_IDTFC3_H +#define PTP_IDTFC3_H + +#include +#include +#include + +#define FW_FILENAME "idtfc3.bin" + +#define MAX_FFO_PPB (244000) +#define TDC_GET_PERIOD (10) + +struct idtfc3 { + struct ptp_clock_info caps; + struct ptp_clock *ptp_clock; + struct device *dev; + /* Mutex to protect operations from being interrupted */ + struct mutex *lock; + struct device *mfd; + struct regmap *regmap; + struct idtfc3_hw_param hw_param; + u32 sub_sync_count; + u32 ns_per_sync; + int tdc_offset_sign; + u64 tdc_apll_freq; + u32 time_ref_freq; + u16 fod_n; + u8 lpf_mode; + /* Time counter */ + u32 last_counter; + s64 ns; + u32 ns_per_counter; + u32 tc_update_period; + u32 tc_write_timeout; + s64 tod_write_overhead; +}; + +#endif /* PTP_IDTFC3_H */ diff --git a/include/linux/mfd/idtRC38xxx_reg.h b/include/linux/mfd/idtRC38xxx_reg.h new file mode 100644 index 000000000000..ec11872f51ad --- /dev/null +++ b/include/linux/mfd/idtRC38xxx_reg.h @@ -0,0 +1,273 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Register Map - Based on PolarBear_CSRs.RevA.xlsx (2023-04-21) + * + * Copyright (C) 2023 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef MFD_IDTRC38XXX_REG +#define MFD_IDTRC38XXX_REG + +/* GLOBAL */ +#define SOFT_RESET_CTRL (0x15) /* Specific to FC3W */ +#define MISC_CTRL (0x14) /* Specific to FC3A */ +#define APLL_REINIT BIT(1) +#define APLL_REINIT_VFC3A BIT(2) + +#define DEVICE_ID (0x2) +#define DEVICE_ID_MASK (0x1000) /* Bit 12 is 1 if FC3W and 0 if FC3A */ +#define DEVICE_ID_SHIFT (12) + +/* FOD */ +#define FOD_0 (0x300) +#define FOD_0_VFC3A (0x400) +#define FOD_1 (0x340) +#define FOD_1_VFC3A (0x440) +#define FOD_2 (0x380) +#define FOD_2_VFC3A (0x480) + +/* TDCAPLL */ +#define TDC_CTRL (0x44a) /* Specific to FC3W */ +#define TDC_ENABLE_CTRL (0x169) /* Specific to FC3A */ +#define TDC_DAC_CAL_CTRL (0x16a) /* Specific to FC3A */ +#define TDC_EN BIT(0) +#define TDC_DAC_RECAL_REQ BIT(1) +#define TDC_DAC_RECAL_REQ_VFC3A BIT(0) + +#define TDC_FB_DIV_INT_CNFG (0x442) +#define TDC_FB_DIV_INT_CNFG_VFC3A (0x162) +#define TDC_FB_DIV_INT_MASK GENMASK(7, 0) +#define TDC_REF_DIV_CNFG (0x443) +#define TDC_REF_DIV_CNFG_VFC3A (0x163) +#define TDC_REF_DIV_CONFIG_MASK GENMASK(2, 0) + +/* TIME SYNC CHANNEL */ +#define TIME_CLOCK_SRC (0xa01) /* Specific to FC3W */ +#define TIME_CLOCK_COUNT (0xa00) /* Specific to FC3W */ +#define TIME_CLOCK_COUNT_MASK GENMASK(5, 0) + +#define SUB_SYNC_GEN_CNFG (0xa04) + +#define TOD_COUNTER_READ_REQ (0xa5f) +#define TOD_COUNTER_READ_REQ_VFC3A (0x6df) +#define TOD_SYNC_LOAD_VAL_CTRL (0xa10) +#define TOD_SYNC_LOAD_VAL_CTRL_VFC3A (0x690) +#define SYNC_COUNTER_MASK GENMASK_ULL(51, 0) +#define SUB_SYNC_COUNTER_MASK GENMASK(30, 0) +#define TOD_SYNC_LOAD_REQ_CTRL (0xa21) +#define TOD_SYNC_LOAD_REQ_CTRL_VFC3A (0x6a1) +#define SYNC_LOAD_ENABLE BIT(1) +#define SUB_SYNC_LOAD_ENABLE BIT(0) +#define SYNC_LOAD_REQ BIT(0) + +#define LPF_MODE_CNFG (0xa80) +#define LPF_MODE_CNFG_VFC3A (0x700) +enum lpf_mode { + LPF_DISABLED = 0, + LPF_WP = 1, + LPF_HOLDOVER = 2, + LPF_WF = 3, + LPF_INVALID = 4 +}; +#define LPF_CTRL (0xa98) +#define LPF_CTRL_VFC3A (0x718) +#define LPF_EN BIT(0) + +#define LPF_BW_CNFG (0xa81) +#define LPF_BW_SHIFT GENMASK(7, 3) +#define LPF_BW_MULT GENMASK(2, 0) +#define LPF_BW_SHIFT_DEFAULT (0xb) +#define LPF_BW_MULT_DEFAULT (0x0) +#define LPF_BW_SHIFT_1PPS (0x5) + +#define LPF_WR_PHASE_CTRL (0xaa8) +#define LPF_WR_PHASE_CTRL_VFC3A (0x728) +#define LPF_WR_FREQ_CTRL (0xab0) +#define LPF_WR_FREQ_CTRL_VFC3A (0x730) + +#define TIME_CLOCK_TDC_FANOUT_CNFG (0xB00) +#define TIME_SYNC_TO_TDC_EN BIT(0) +#define SIG1_MUX_SEL_MASK GENMASK(7, 4) +#define SIG2_MUX_SEL_MASK GENMASK(11, 8) +enum tdc_mux_sel { + REF0 = 0, + REF1 = 1, + REF2 = 2, + REF3 = 3, + REF_CLK5 = 4, + REF_CLK6 = 5, + DPLL_FB_TO_TDC = 6, + DPLL_FB_DIVIDED_TO_TDC = 7, + TIME_CLK_DIVIDED = 8, + TIME_SYNC = 9, +}; + +#define TIME_CLOCK_MEAS_CNFG (0xB04) +#define TDC_MEAS_MODE BIT(0) +enum tdc_meas_mode { + CONTINUOUS = 0, + ONE_SHOT = 1, + MEAS_MODE_INVALID = 2, +}; + +#define TIME_CLOCK_MEAS_DIV_CNFG (0xB08) +#define TIME_REF_DIV_MASK GENMASK(29, 24) + +#define TIME_CLOCK_MEAS_CTRL (0xB10) +#define TDC_MEAS_EN BIT(0) +#define TDC_MEAS_START BIT(1) + +#define TDC_FIFO_READ_REQ (0xB2F) +#define TDC_FIFO_READ (0xB30) +#define COARSE_MEAS_MASK GENMASK_ULL(39, 13) +#define FINE_MEAS_MASK GENMASK(12, 0) + +#define TDC_FIFO_CTRL (0xB12) +#define FIFO_CLEAR BIT(0) +#define TDC_FIFO_STS (0xB38) +#define FIFO_FULL BIT(1) +#define FIFO_EMPTY BIT(0) +#define TDC_FIFO_EVENT (0xB39) +#define FIFO_OVERRUN BIT(1) + +/* DPLL */ +#define MAX_REFERENCE_INDEX (3) +#define MAX_NUM_REF_PRIORITY (4) + +#define MAX_DPLL_INDEX (2) + +#define DPLL_STS (0x580) +#define DPLL_STS_VFC3A (0x571) +#define DPLL_STATE_STS_MASK (0x70) +#define DPLL_STATE_STS_SHIFT (4) +#define DPLL_REF_SEL_STS_MASK (0x6) +#define DPLL_REF_SEL_STS_SHIFT (1) + +#define DPLL_REF_PRIORITY_CNFG (0x502) +#define DPLL_REFX_PRIORITY_DISABLE_MASK (0xf) +#define DPLL_REF0_PRIORITY_ENABLE_AND_SET_MASK (0x31) +#define DPLL_REF1_PRIORITY_ENABLE_AND_SET_MASK (0xc2) +#define DPLL_REF2_PRIORITY_ENABLE_AND_SET_MASK (0x304) +#define DPLL_REF3_PRIORITY_ENABLE_AND_SET_MASK (0xc08) +#define DPLL_REF0_PRIORITY_SHIFT (4) +#define DPLL_REF1_PRIORITY_SHIFT (6) +#define DPLL_REF2_PRIORITY_SHIFT (8) +#define DPLL_REF3_PRIORITY_SHIFT (10) + +enum dpll_state { + DPLL_STATE_MIN = 0, + DPLL_STATE_FREERUN = DPLL_STATE_MIN, + DPLL_STATE_LOCKED = 1, + DPLL_STATE_HOLDOVER = 2, + DPLL_STATE_WRITE_FREQUENCY = 3, + DPLL_STATE_ACQUIRE = 4, + DPLL_STATE_HITLESS_SWITCH = 5, + DPLL_STATE_MAX = DPLL_STATE_HITLESS_SWITCH +}; + +/* REFMON */ +#define LOSMON_STS_0 (0x81e) +#define LOSMON_STS_0_VFC3A (0x18e) +#define LOSMON_STS_1 (0x82e) +#define LOSMON_STS_1_VFC3A (0x19e) +#define LOSMON_STS_2 (0x83e) +#define LOSMON_STS_2_VFC3A (0x1ae) +#define LOSMON_STS_3 (0x84e) +#define LOSMON_STS_3_VFC3A (0x1be) +#define LOS_STS_MASK (0x1) + +#define FREQMON_STS_0 (0x874) +#define FREQMON_STS_0_VFC3A (0x1d4) +#define FREQMON_STS_1 (0x894) +#define FREQMON_STS_1_VFC3A (0x1f4) +#define FREQMON_STS_2 (0x8b4) +#define FREQMON_STS_2_VFC3A (0x214) +#define FREQMON_STS_3 (0x8d4) +#define FREQMON_STS_3_VFC3A (0x234) +#define FREQ_FAIL_STS_SHIFT (31) + +/* Firmware interface */ +#define TIME_CLK_FREQ_ADDR (0xffa0) +#define XTAL_FREQ_ADDR (0xffa1) + +/* + * Return register address and field mask based on passed in firmware version + */ +#define IDTFC3_FW_REG(FW, VER, REG) (((FW) < (VER)) ? (REG) : (REG##_##VER)) +#define IDTFC3_FW_FIELD(FW, VER, FIELD) (((FW) < (VER)) ? (FIELD) : (FIELD##_##VER)) +enum fw_version { + V_DEFAULT = 0, + VFC3W = 1, + VFC3A = 2 +}; + +/* XTAL_FREQ_ADDR/TIME_CLK_FREQ_ADDR */ +enum { + FREQ_MIN = 0, + FREQ_25M = 1, + FREQ_49_152M = 2, + FREQ_50M = 3, + FREQ_100M = 4, + FREQ_125M = 5, + FREQ_250M = 6, + FREQ_MAX +}; + +struct idtfc3_hw_param { + u32 xtal_freq; + u32 time_clk_freq; +}; + +struct idtfc3_fwrc { + u8 hiaddr; + u8 loaddr; + u8 value; + u8 reserved; +} __packed; + +static inline void idtfc3_default_hw_param(struct idtfc3_hw_param *hw_param) +{ + hw_param->xtal_freq = 49152000; + hw_param->time_clk_freq = 25000000; +} + +static inline int idtfc3_set_hw_param(struct idtfc3_hw_param *hw_param, + u16 addr, u8 val) +{ + if (addr == XTAL_FREQ_ADDR) + switch (val) { + case FREQ_49_152M: + hw_param->xtal_freq = 49152000; + break; + case FREQ_50M: + hw_param->xtal_freq = 50000000; + break; + default: + return -EINVAL; + } + else if (addr == TIME_CLK_FREQ_ADDR) + switch (val) { + case FREQ_25M: + hw_param->time_clk_freq = 25000000; + break; + case FREQ_50M: + hw_param->time_clk_freq = 50000000; + break; + case FREQ_100M: + hw_param->time_clk_freq = 100000000; + break; + case FREQ_125M: + hw_param->time_clk_freq = 125000000; + break; + case FREQ_250M: + hw_param->time_clk_freq = 250000000; + break; + default: + return -EINVAL; + } + else + return -EFAULT; + + return 0; +} + +#endif -- cgit v1.2.3 From efaa47db92451608499ab7edf108bf30141c33db Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 28 Jan 2024 13:54:43 +0800 Subject: bpf: Remove unused field "mod" in struct bpf_trampoline It seems that the field "mod" in struct bpf_trampoline is not used anywhere after the commit 31bf1dbccfb0 ("bpf: Fix attaching fentry/fexit/fmod_ret/lsm to modules"). So we can just remove it now. Fixes: 31bf1dbccfb0 ("bpf: Fix attaching fentry/fexit/fmod_ret/lsm to modules") Signed-off-by: Menglong Dong Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240128055443.413291-1-dongmenglong.8@bytedance.com --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b86bd15a051d..1ebbee1d648e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1189,7 +1189,6 @@ struct bpf_trampoline { int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; - struct module *mod; }; struct bpf_attach_target_info { -- cgit v1.2.3 From e2b3c4ff5d183da6d1863c2321413406a2752e7a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 29 Jan 2024 16:06:45 -0800 Subject: bpf: add __arg_trusted global func arg tag Add support for passing PTR_TO_BTF_ID registers to global subprogs. Currently only PTR_TRUSTED flavor of PTR_TO_BTF_ID is supported. Non-NULL semantics is assumed, so caller will be forced to prove PTR_TO_BTF_ID can't be NULL. Note, we disallow global subprogs to destroy passed in PTR_TO_BTF_ID arguments, even the trusted one. We achieve that by not setting ref_obj_id when validating subprog code. This basically enforces (in Rust terms) borrowing semantics vs move semantics. Borrowing semantics seems to be a better fit for isolated global subprog validation approach. Implementation-wise, we utilize existing logic for matching user-provided BTF type to kernel-side BTF type, used by BPF CO-RE logic and following same matching rules. We enforce a unique match for types. Acked-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240130000648.2144827-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/btf.c | 99 ++++++++++++++++++++++++++++++++++++++------ kernel/bpf/verifier.c | 24 +++++++++++ 3 files changed, 111 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7f5816482a10..0dcde339dc7e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -610,6 +610,7 @@ struct bpf_subprog_arg_info { enum bpf_arg_type arg_type; union { u32 mem_size; + u32 btf_id; }; }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9ec08cfb2967..ed7a05815984 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6985,9 +6985,77 @@ static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) return false; } +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static DEFINE_MUTEX(cand_cache_mutex); + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); + +static int btf_get_ptr_to_btf_id(struct bpf_verifier_log *log, int arg_idx, + const struct btf *btf, const struct btf_type *t) +{ + struct bpf_cand_cache *cc; + struct bpf_core_ctx ctx = { + .btf = btf, + .log = log, + }; + u32 kern_type_id, type_id; + int err = 0; + + /* skip PTR and modifiers */ + type_id = t->type; + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) { + type_id = t->type; + t = btf_type_by_id(btf, t->type); + } + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(&ctx, type_id); + if (IS_ERR(cc)) { + err = PTR_ERR(cc); + bpf_log(log, "arg#%d reference type('%s %s') candidate matching error: %d\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + err); + goto cand_cache_unlock; + } + if (cc->cnt != 1) { + bpf_log(log, "arg#%d reference type('%s %s') %s\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + cc->cnt == 0 ? "has no matches" : "is ambiguous"); + err = cc->cnt == 0 ? -ENOENT : -ESRCH; + goto cand_cache_unlock; + } + if (btf_is_module(cc->cands[0].btf)) { + bpf_log(log, "arg#%d reference type('%s %s') points to kernel module type (unsupported)\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + err = -EOPNOTSUPP; + goto cand_cache_unlock; + } + kern_type_id = cc->cands[0].id; + +cand_cache_unlock: + mutex_unlock(&cand_cache_mutex); + if (err) + return err; + + return kern_type_id; +} + enum btf_arg_tag { ARG_TAG_CTX = 0x1, ARG_TAG_NONNULL = 0x2, + ARG_TAG_TRUSTED = 0x4, }; /* Process BTF of a function to produce high-level expectation of function @@ -7089,6 +7157,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) if (strcmp(tag, "ctx") == 0) { tags |= ARG_TAG_CTX; + } else if (strcmp(tag, "trusted") == 0) { + tags |= ARG_TAG_TRUSTED; } else if (strcmp(tag, "nonnull") == 0) { tags |= ARG_TAG_NONNULL; } else { @@ -7127,6 +7197,22 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; continue; } + if (tags & ARG_TAG_TRUSTED) { + int kern_type_id; + + if (tags & ARG_TAG_NONNULL) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + + kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); + if (kern_type_id < 0) + return kern_type_id; + + sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_TRUSTED; + sub->args[i].btf_id = kern_type_id; + continue; + } if (is_global) { /* generic user data pointer */ u32 mem_size; @@ -8229,17 +8315,6 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -struct bpf_cand_cache { - const char *name; - u32 name_len; - u16 kind; - u16 cnt; - struct { - const struct btf *btf; - u32 id; - } cands[]; -}; - static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) @@ -8260,8 +8335,6 @@ static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; -static DEFINE_MUTEX(cand_cache_mutex); - static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c5d68a9d8acc..cd4d780e5400 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9336,6 +9336,18 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) return ret; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + struct bpf_call_arg_meta meta; + int err; + + if (register_is_null(reg) && type_may_be_null(arg->arg_type)) + continue; + + memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ + err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); + err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); + if (err) + return err; } else { bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", i, arg->arg_type); @@ -20137,6 +20149,18 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, i); reg->mem_size = arg->mem_size; reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + reg->type = PTR_TO_BTF_ID; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; + if (arg->arg_type & PTR_UNTRUSTED) + reg->type |= PTR_UNTRUSTED; + if (arg->arg_type & PTR_TRUSTED) + reg->type |= PTR_TRUSTED; + mark_reg_known_zero(env, regs, i); + reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ + reg->btf_id = arg->btf_id; + reg->id = ++env->id_gen; } else { WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", i - BPF_REG_1, arg->arg_type); -- cgit v1.2.3 From c5c3e1bfc9e0ee72af528df8d773980f4855938a Mon Sep 17 00:00:00 2001 From: Rohan G Thomas Date: Sat, 27 Jan 2024 12:04:41 +0800 Subject: net: stmmac: Offload queueMaxSDU from tc-taprio Add support for configuring queueMaxSDU. As DWMAC IPs doesn't support queueMaxSDU table handle this in the SW. The maximum 802.3 frame size that is allowed to be transmitted by any queue is queueMaxSDU + 16 bytes (i.e. 6 bytes SA + 6 bytes DA + 4 bytes FCS). Inspired from intel i225 driver. Signed-off-by: Rohan G Thomas Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 22 ++++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 25 +++++++++++++++++++++++ include/linux/stmmac.h | 1 + 4 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 721c1f8e892f..d8d2a90fd228 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -202,6 +202,7 @@ struct stmmac_extra_stats { unsigned long mtl_est_hlbf; unsigned long mtl_est_btre; unsigned long mtl_est_btrlm; + unsigned long max_sdu_txq_drop[MTL_MAX_TX_QUEUES]; /* per queue statistics */ struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES]; struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES]; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b334eb16da23..33509237fe60 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2507,6 +2507,13 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) if (!xsk_tx_peek_desc(pool, &xdp_desc)) break; + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + xdp_desc.len > priv->plat->est->max_sdu[queue]) { + priv->xstats.max_sdu_txq_drop[queue]++; + continue; + } + if (likely(priv->extend_desc)) tx_desc = (struct dma_desc *)(tx_q->dma_etx + entry); else if (tx_q->tbs & STMMAC_TBS_AVAIL) @@ -4498,6 +4505,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return stmmac_tso_xmit(skb, dev); } + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + skb->len > priv->plat->est->max_sdu[queue]){ + priv->xstats.max_sdu_txq_drop[queue]++; + goto max_sdu_err; + } + if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, @@ -4715,6 +4729,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dma_map_err: netdev_err(priv->dev, "Tx DMA map failed\n"); +max_sdu_err: dev_kfree_skb(skb); priv->xstats.tx_dropped++; return NETDEV_TX_OK; @@ -4871,6 +4886,13 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, if (stmmac_tx_avail(priv, queue) < STMMAC_TX_THRESH(priv)) return STMMAC_XDP_CONSUMED; + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + xdpf->len > priv->plat->est->max_sdu[queue]) { + priv->xstats.max_sdu_txq_drop[queue]++; + return STMMAC_XDP_CONSUMED; + } + if (likely(priv->extend_desc)) tx_desc = (struct dma_desc *)(tx_q->dma_etx + entry); else if (tx_q->tbs & STMMAC_TBS_AVAIL) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 26fa33e5ec34..07aa3a3089dc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -915,6 +915,28 @@ struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, return time; } +static void tc_taprio_map_maxsdu_txq(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) +{ + struct plat_stmmacenet_data *plat = priv->plat; + u32 num_tc = qopt->mqprio.qopt.num_tc; + u32 offset, count, i, j; + + /* QueueMaxSDU received from the driver corresponds to the Linux traffic + * class. Map queueMaxSDU per Linux traffic class to DWMAC Tx queues. + */ + for (i = 0; i < num_tc; i++) { + if (!qopt->max_sdu[i]) + continue; + + offset = qopt->mqprio.qopt.offset[i]; + count = qopt->mqprio.qopt.count[i]; + + for (j = offset; j < offset + count; j++) + plat->est->max_sdu[j] = qopt->max_sdu[i] + ETH_HLEN - ETH_TLEN; + } +} + static int tc_setup_taprio(struct stmmac_priv *priv, struct tc_taprio_qopt_offload *qopt) { @@ -1045,6 +1067,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ter = qopt->cycle_time_extension; + tc_taprio_map_maxsdu_txq(priv, qopt); + if (fpe && !priv->dma_cap.fpesel) { mutex_unlock(&priv->plat->est->lock); return -EOPNOTSUPP; @@ -1126,6 +1150,7 @@ static int tc_query_caps(struct stmmac_priv *priv, return -EOPNOTSUPP; caps->gate_mask_per_txq = true; + caps->supports_queue_max_sdu = true; return 0; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dee5ad6e48c5..dfa1828cd756 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -127,6 +127,7 @@ struct stmmac_est { u32 gcl_unaligned[EST_GCL]; u32 gcl[EST_GCL]; u32 gcl_size; + u32 max_sdu[MTL_MAX_TX_QUEUES]; }; struct stmmac_rxq_cfg { -- cgit v1.2.3 From d80a52335374e484a4ff2afdc9af843e73273945 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jan 2024 14:25:09 +0100 Subject: ethtool: replace struct ethtool_eee with a new struct ethtool_keee on kernel side In order to pass EEE link modes beyond bit 32 to userspace we have to complement the 32 bit bitmaps in struct ethtool_eee with linkmode bitmaps. Therefore, similar to ethtool_link_settings and ethtool_link_ksettings, add a struct ethtool_keee. In a first step it's an identical copy of ethtool_eee. This patch simply does a s/ethtool_eee/ethtool_keee/g for all users. No functional change intended. Suggested-by: Andrew Lunn Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 10 +++++----- drivers/net/dsa/b53/b53_priv.h | 6 +++--- drivers/net/dsa/bcm_sf2.c | 2 +- drivers/net/dsa/microchip/ksz_common.c | 4 ++-- drivers/net/dsa/mt7530.c | 4 ++-- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- drivers/net/dsa/qca/qca8k-common.c | 4 ++-- drivers/net/dsa/qca/qca8k.h | 4 ++-- drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 4 ++-- drivers/net/ethernet/broadcom/asp2/bcmasp.h | 2 +- drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c | 8 ++++---- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 ++-- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++---- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 6 +++--- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 ++++---- drivers/net/ethernet/broadcom/genet/bcmgenet.h | 2 +- drivers/net/ethernet/broadcom/tg3.c | 10 +++++----- drivers/net/ethernet/broadcom/tg3.h | 2 +- drivers/net/ethernet/engleder/tsnep_main.c | 6 +++--- drivers/net/ethernet/freescale/enetc/enetc.c | 4 ++-- drivers/net/ethernet/freescale/fec.h | 2 +- drivers/net/ethernet/freescale/fec_main.c | 10 +++++----- drivers/net/ethernet/freescale/gianfar.c | 4 ++-- drivers/net/ethernet/intel/e1000e/ethtool.c | 6 +++--- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 6 +++--- drivers/net/ethernet/intel/igb/igb_ethtool.c | 8 ++++---- drivers/net/ethernet/intel/igc/igc.h | 2 +- drivers/net/ethernet/intel/igc/igc_ethtool.c | 8 ++++---- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 10 +++++----- drivers/net/ethernet/marvell/mvneta.c | 4 ++-- drivers/net/ethernet/microchip/lan743x_ethtool.c | 4 ++-- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 4 ++-- drivers/net/ethernet/realtek/r8169_main.c | 4 ++-- drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 4 ++-- drivers/net/ethernet/ti/am65-cpsw-ethtool.c | 4 ++-- drivers/net/ethernet/ti/cpsw_ethtool.c | 4 ++-- drivers/net/ethernet/ti/cpsw_priv.h | 4 ++-- drivers/net/ethernet/ti/icssg/icssg_ethtool.c | 4 ++-- drivers/net/phy/marvell.c | 2 +- drivers/net/phy/phy-c45.c | 8 ++++---- drivers/net/phy/phy.c | 8 ++++---- drivers/net/phy/phylink.c | 8 ++++---- drivers/net/usb/ax88179_178a.c | 10 +++++----- drivers/net/usb/lan78xx.c | 4 ++-- drivers/net/usb/r8152.c | 14 +++++++------- include/linux/ethtool.h | 16 ++++++++++++++-- include/linux/phy.h | 8 ++++---- include/linux/phylink.h | 4 ++-- include/net/dsa.h | 4 ++-- net/dsa/user.c | 4 ++-- net/ethtool/eee.c | 10 +++++----- net/ethtool/ioctl.c | 6 +++--- 54 files changed, 159 insertions(+), 147 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 0d628b35fd5c..adc93abf4551 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1257,7 +1257,7 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phydev) { struct b53_device *dev = ds->priv; - struct ethtool_eee *p = &dev->ports[port].eee; + struct ethtool_keee *p = &dev->ports[port].eee; u8 rgmii_ctrl = 0, reg = 0, off; bool tx_pause = false; bool rx_pause = false; @@ -2224,10 +2224,10 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy) } EXPORT_SYMBOL(b53_eee_init); -int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e) +int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { struct b53_device *dev = ds->priv; - struct ethtool_eee *p = &dev->ports[port].eee; + struct ethtool_keee *p = &dev->ports[port].eee; u16 reg; if (is5325(dev) || is5365(dev)) @@ -2241,10 +2241,10 @@ int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e) } EXPORT_SYMBOL(b53_get_mac_eee); -int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e) +int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { struct b53_device *dev = ds->priv; - struct ethtool_eee *p = &dev->ports[port].eee; + struct ethtool_keee *p = &dev->ports[port].eee; if (is5325(dev) || is5365(dev)) return -EOPNOTSUPP; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index fdcfd5081c28..c26a03755e83 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -95,7 +95,7 @@ struct b53_pcs { struct b53_port { u16 vlan_ctl_mask; - struct ethtool_eee eee; + struct ethtool_keee eee; }; struct b53_vlan { @@ -397,7 +397,7 @@ void b53_disable_port(struct dsa_switch *ds, int port); void b53_brcm_hdr_setup(struct dsa_switch *ds, int port); void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable); int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy); -int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); -int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); +int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); +int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); #endif diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 4a52ccbe393f..bc77ee9e6d0a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -835,7 +835,7 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, bool tx_pause, bool rx_pause) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct ethtool_eee *p = &priv->dev->ports[port].eee; + struct ethtool_keee *p = &priv->dev->ports[port].eee; u32 reg_rgmii_ctrl = 0; u32 reg, offset; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 245dfb7a7a31..a7b5ddb8656e 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2852,7 +2852,7 @@ static int ksz_validate_eee(struct dsa_switch *ds, int port) } static int ksz_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { int ret; @@ -2872,7 +2872,7 @@ static int ksz_get_mac_eee(struct dsa_switch *ds, int port, } static int ksz_set_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { struct ksz_device *dev = ds->priv; int ret; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 68be38ae66e0..98a73a62f2ee 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -3048,7 +3048,7 @@ mt753x_setup(struct dsa_switch *ds) } static int mt753x_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { struct mt7530_priv *priv = ds->priv; u32 eeecr = mt7530_read(priv, MT7530_PMEEECR_P(port)); @@ -3060,7 +3060,7 @@ static int mt753x_get_mac_eee(struct dsa_switch *ds, int port, } static int mt753x_set_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { struct mt7530_priv *priv = ds->priv; u32 set, mask = LPI_THRESH_MASK | LPI_MODE_EN; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 383b3c4d6f59..8b0079b8e0e0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1451,14 +1451,14 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, } static int mv88e6xxx_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { /* Nothing to do on the port's MAC */ return 0; } static int mv88e6xxx_set_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { /* Nothing to do on the port's MAC */ return 0; diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 2358cd399c7e..7f80035c5441 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -534,7 +534,7 @@ int qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset) } int qca8k_set_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *eee) + struct ethtool_keee *eee) { u32 lpi_en = QCA8K_REG_EEE_CTRL_LPI_EN(port); struct qca8k_priv *priv = ds->priv; @@ -558,7 +558,7 @@ exit: } int qca8k_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_eee *e) + struct ethtool_keee *e) { /* Nothing to do on the port's MAC */ return 0; diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h index c8785c36c54e..2184d8d2d5a9 100644 --- a/drivers/net/dsa/qca/qca8k.h +++ b/drivers/net/dsa/qca/qca8k.h @@ -518,8 +518,8 @@ void qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, int qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset); /* Common eee function */ -int qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *eee); -int qca8k_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); +int qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *eee); +int qca8k_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* Common bridge function */ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 18a6c8d99fa0..be865776de55 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -697,7 +697,7 @@ static u32 eee_mask_to_ethtool_mask(u32 speed) return rate; } -static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_eee *eee) +static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_keee *eee) { struct aq_nic_s *aq_nic = netdev_priv(ndev); u32 rate, supported_rates; @@ -729,7 +729,7 @@ static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_eee *eee) return 0; } -static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_eee *eee) +static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_keee *eee) { struct aq_nic_s *aq_nic = netdev_priv(ndev); u32 rate, supported_rates; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index ec90add6b03e..312bf9b6576e 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -337,7 +337,7 @@ struct bcmasp_intf { int wol_irq; unsigned int wol_irq_enabled:1; - struct ethtool_eee eee; + struct ethtool_keee eee; }; #define NUM_NET_FILTERS 32 diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index ce6a3d56fb23..2851bed153e6 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -363,10 +363,10 @@ void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable) intf->eee.eee_active = enable; } -static int bcmasp_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int bcmasp_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_eee *p = &intf->eee; + struct ethtool_keee *p = &intf->eee; if (!dev->phydev) return -ENODEV; @@ -379,10 +379,10 @@ static int bcmasp_get_eee(struct net_device *dev, struct ethtool_eee *e) return phy_ethtool_get_eee(dev->phydev, e); } -static int bcmasp_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int bcmasp_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_eee *p = &intf->eee; + struct ethtool_keee *p = &intf->eee; int ret; if (!dev->phydev) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 0bc7690cdee1..12d2785eeb8a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2108,7 +2108,7 @@ static u32 bnx2x_adv_to_eee(u32 modes, u32 shift) return eee_adv << shift; } -static int bnx2x_get_eee(struct net_device *dev, struct ethtool_eee *edata) +static int bnx2x_get_eee(struct net_device *dev, struct ethtool_keee *edata) { struct bnx2x *bp = netdev_priv(dev); u32 eee_cfg; @@ -2141,7 +2141,7 @@ static int bnx2x_get_eee(struct net_device *dev, struct ethtool_eee *edata) return 0; } -static int bnx2x_set_eee(struct net_device *dev, struct ethtool_eee *edata) +static int bnx2x_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct bnx2x *bp = netdev_priv(dev); u32 eee_cfg; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 39845d556baf..d7626c26f9a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10621,7 +10621,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) bp->phy_flags = resp->flags | (le16_to_cpu(resp->flags2) << 8); if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED) { - struct ethtool_eee *eee = &bp->eee; + struct ethtool_keee *eee = &bp->eee; u16 fw_speeds = le16_to_cpu(resp->supported_speeds_eee_mode); eee->supported = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); @@ -10766,7 +10766,7 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state) link_info->module_status = resp->module_status; if (bp->phy_flags & BNXT_PHY_FL_EEE_CAP) { - struct ethtool_eee *eee = &bp->eee; + struct ethtool_keee *eee = &bp->eee; u16 fw_speeds; eee->eee_active = 0; @@ -10957,7 +10957,7 @@ int bnxt_hwrm_set_pause(struct bnxt *bp) static void bnxt_hwrm_set_eee(struct bnxt *bp, struct hwrm_port_phy_cfg_input *req) { - struct ethtool_eee *eee = &bp->eee; + struct ethtool_keee *eee = &bp->eee; if (eee->eee_enabled) { u16 eee_speeds; @@ -11322,7 +11322,7 @@ static void bnxt_get_wol_settings(struct bnxt *bp) static bool bnxt_eee_config_ok(struct bnxt *bp) { - struct ethtool_eee *eee = &bp->eee; + struct ethtool_keee *eee = &bp->eee; struct bnxt_link_info *link_info = &bp->link_info; if (!(bp->phy_flags & BNXT_PHY_FL_EEE_CAP)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 47338b48ca20..b2cb3e77559d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2442,7 +2442,7 @@ struct bnxt { */ struct mutex link_lock; struct bnxt_link_info link_info; - struct ethtool_eee eee; + struct ethtool_keee eee; u32 lpi_tmr_lo; u32 lpi_tmr_hi; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index dc4ca706b0e2..d6a8577d68af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3884,10 +3884,10 @@ static int bnxt_set_eeprom(struct net_device *dev, eeprom->len); } -static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) +static int bnxt_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct bnxt *bp = netdev_priv(dev); - struct ethtool_eee *eee = &bp->eee; + struct ethtool_keee *eee = &bp->eee; struct bnxt_link_info *link_info = &bp->link_info; u32 advertising; int rc = 0; @@ -3942,7 +3942,7 @@ eee_exit: return rc; } -static int bnxt_get_eee(struct net_device *dev, struct ethtool_eee *edata) +static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata) { struct bnxt *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2d7ae71287b1..051c31fb17c2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1317,10 +1317,10 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, priv->eee.tx_lpi_enabled = tx_lpi_enabled; } -static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_eee *p = &priv->eee; + struct ethtool_keee *p = &priv->eee; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1336,10 +1336,10 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) return phy_ethtool_get_eee(dev->phydev, e); } -static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_eee *p = &priv->eee; + struct ethtool_keee *p = &priv->eee; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 1985c0ec4da2..7523b60b3c1c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -645,7 +645,7 @@ struct bcmgenet_priv { struct bcmgenet_mib_counters mib; - struct ethtool_eee eee; + struct ethtool_keee eee; }; #define GENET_IO_MACRO(name, offset) \ diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 04964bbe08cf..11054177c2ec 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -2338,10 +2338,10 @@ static void tg3_phy_apply_otp(struct tg3 *tp) tg3_phy_toggle_auxctl_smdsp(tp, false); } -static void tg3_eee_pull_config(struct tg3 *tp, struct ethtool_eee *eee) +static void tg3_eee_pull_config(struct tg3 *tp, struct ethtool_keee *eee) { u32 val; - struct ethtool_eee *dest = &tp->eee; + struct ethtool_keee *dest = &tp->eee; if (!(tp->phy_flags & TG3_PHYFLG_EEE_CAP)) return; @@ -4618,7 +4618,7 @@ static int tg3_init_5401phy_dsp(struct tg3 *tp) static bool tg3_phy_eee_config_ok(struct tg3 *tp) { - struct ethtool_eee eee; + struct ethtool_keee eee; if (!(tp->phy_flags & TG3_PHYFLG_EEE_CAP)) return true; @@ -14180,7 +14180,7 @@ static int tg3_set_coalesce(struct net_device *dev, return 0; } -static int tg3_set_eee(struct net_device *dev, struct ethtool_eee *edata) +static int tg3_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct tg3 *tp = netdev_priv(dev); @@ -14217,7 +14217,7 @@ static int tg3_set_eee(struct net_device *dev, struct ethtool_eee *edata) return 0; } -static int tg3_get_eee(struct net_device *dev, struct ethtool_eee *edata) +static int tg3_get_eee(struct net_device *dev, struct ethtool_keee *edata) { struct tg3 *tp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 5016475e5005..cf1b2b123c7e 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3419,7 +3419,7 @@ struct tg3 { unsigned int irq_cnt; struct ethtool_coalesce coal; - struct ethtool_eee eee; + struct ethtool_keee eee; /* firmware info */ const char *fw_needed; diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index ae0b8b37b9bf..eb64118f5b18 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -240,7 +240,7 @@ static int tsnep_phy_loopback(struct tsnep_adapter *adapter, bool enable) static int tsnep_phy_open(struct tsnep_adapter *adapter) { struct phy_device *phydev; - struct ethtool_eee ethtool_eee; + struct ethtool_keee ethtool_keee; int retval; retval = phy_connect_direct(adapter->netdev, adapter->phydev, @@ -259,8 +259,8 @@ static int tsnep_phy_open(struct tsnep_adapter *adapter) phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* disable EEE autoneg, EEE not supported by TSNEP */ - memset(ðtool_eee, 0, sizeof(ethtool_eee)); - phy_ethtool_set_eee(adapter->phydev, ðtool_eee); + memset(ðtool_keee, 0, sizeof(ethtool_keee)); + phy_ethtool_set_eee(adapter->phydev, ðtool_keee); adapter->phydev->irq = PHY_MAC_INTERRUPT; phy_start(adapter->phydev); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index bfdbdab443ae..9f07f4947b63 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2402,7 +2402,7 @@ static void enetc_clear_interrupts(struct enetc_ndev_priv *priv) static int enetc_phylink_connect(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct ethtool_eee edata; + struct ethtool_keee edata; int err; if (!priv->phylink) { @@ -2418,7 +2418,7 @@ static int enetc_phylink_connect(struct net_device *ndev) } /* disable EEE autoneg, until ENETC driver supports it */ - memset(&edata, 0, sizeof(struct ethtool_eee)); + memset(&edata, 0, sizeof(struct ethtool_keee)); phylink_ethtool_set_eee(priv->phylink, &edata); phylink_start(priv->phylink); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index a8fbcada6b01..a19cb2a786fd 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -672,7 +672,7 @@ struct fec_enet_private { unsigned int itr_clk_rate; /* tx lpi eee mode */ - struct ethtool_eee eee; + struct ethtool_keee eee; unsigned int clk_ref_rate; /* ptp clock period in ns*/ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 432523b2c789..63707e065141 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3122,7 +3122,7 @@ static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us) static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_eee *p = &fep->eee; + struct ethtool_keee *p = &fep->eee; unsigned int sleep_cycle, wake_cycle; int ret = 0; @@ -3149,10 +3149,10 @@ static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) } static int -fec_enet_get_eee(struct net_device *ndev, struct ethtool_eee *edata) +fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_eee *p = &fep->eee; + struct ethtool_keee *p = &fep->eee; if (!(fep->quirks & FEC_QUIRK_HAS_EEE)) return -EOPNOTSUPP; @@ -3169,10 +3169,10 @@ fec_enet_get_eee(struct net_device *ndev, struct ethtool_eee *edata) } static int -fec_enet_set_eee(struct net_device *ndev, struct ethtool_eee *edata) +fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_eee *p = &fep->eee; + struct ethtool_keee *p = &fep->eee; int ret = 0; if (!(fep->quirks & FEC_QUIRK_HAS_EEE)) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index e3dfbd7a4236..a811238c018d 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1649,7 +1649,7 @@ static int init_phy(struct net_device *dev) struct gfar_private *priv = netdev_priv(dev); phy_interface_t interface = priv->interface; struct phy_device *phydev; - struct ethtool_eee edata; + struct ethtool_keee edata; linkmode_set_bit_array(phy_10_100_features_array, ARRAY_SIZE(phy_10_100_features_array), @@ -1681,7 +1681,7 @@ static int init_phy(struct net_device *dev) phy_support_asym_pause(phydev); /* disable EEE autoneg, EEE not supported by eTSEC */ - memset(&edata, 0, sizeof(struct ethtool_eee)); + memset(&edata, 0, sizeof(struct ethtool_keee)); phy_ethtool_set_eee(phydev, &edata); return 0; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index fc0f98ea6133..343f54b2b6ae 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -2186,7 +2186,7 @@ static int e1000_get_rxnfc(struct net_device *netdev, } } -static int e1000e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -2262,11 +2262,11 @@ release: return ret_val; } -static int e1000e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int e1000e_set_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - struct ethtool_eee eee_curr; + struct ethtool_keee eee_curr; s32 ret_val; ret_val = e1000e_get_eee(netdev, &eee_curr); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index c841779713f6..9dfda3c48af3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5644,7 +5644,7 @@ static int i40e_get_module_eeprom(struct net_device *netdev, return 0; } -static int i40e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp phy_cfg; @@ -5682,7 +5682,7 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) } static int i40e_is_eee_param_supported(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -5709,7 +5709,7 @@ static int i40e_is_eee_param_supported(struct net_device *netdev, return 0; } -static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int i40e_set_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index b66199c9bb3a..778d1e6cfc45 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -3027,7 +3027,7 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } -static int igb_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -3106,11 +3106,11 @@ static int igb_get_eee(struct net_device *netdev, struct ethtool_eee *edata) } static int igb_set_eee(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - struct ethtool_eee eee_curr; + struct ethtool_keee eee_curr; bool adv1g_eee = true, adv100m_eee = true; s32 ret_val; @@ -3118,7 +3118,7 @@ static int igb_set_eee(struct net_device *netdev, (hw->phy.media_type != e1000_media_type_copper)) return -EOPNOTSUPP; - memset(&eee_curr, 0, sizeof(struct ethtool_eee)); + memset(&eee_curr, 0, sizeof(struct ethtool_keee)); ret_val = igb_get_eee(netdev, &eee_curr); if (ret_val) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 45430e246e9c..75f7c5ba65e0 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -168,7 +168,7 @@ struct igc_ring { struct igc_adapter { struct net_device *netdev; - struct ethtool_eee eee; + struct ethtool_keee eee; u16 eee_advert; unsigned long state; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index b95d2c86e803..f2dcfe920f4f 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1623,7 +1623,7 @@ static int igc_ethtool_set_priv_flags(struct net_device *netdev, u32 priv_flags) } static int igc_ethtool_get_eee(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_hw *hw = &adapter->hw; @@ -1664,14 +1664,14 @@ static int igc_ethtool_get_eee(struct net_device *netdev, } static int igc_ethtool_set_eee(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_hw *hw = &adapter->hw; - struct ethtool_eee eee_curr; + struct ethtool_keee eee_curr; s32 ret_val; - memset(&eee_curr, 0, sizeof(struct ethtool_eee)); + memset(&eee_curr, 0, sizeof(struct ethtool_keee)); ret_val = igc_ethtool_get_eee(netdev, &eee_curr); if (ret_val) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 9a63457712c7..0aa73519a29d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3425,7 +3425,7 @@ static const struct { }; static int -ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_eee *edata) +ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata) { u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; struct ixgbe_hw *hw = &adapter->hw; @@ -3462,7 +3462,7 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_eee *edata) return 0; } -static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -3476,17 +3476,17 @@ static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_eee *edata) return -EOPNOTSUPP; } -static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_eee *edata) +static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - struct ethtool_eee eee_data; + struct ethtool_keee eee_data; s32 ret_val; if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) return -EOPNOTSUPP; - memset(&eee_data, 0, sizeof(struct ethtool_eee)); + memset(&eee_data, 0, sizeof(struct ethtool_keee)); ret_val = ixgbe_get_eee(netdev, &eee_data); if (ret_val) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index a641b3534ca3..40a5f1431e4e 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5097,7 +5097,7 @@ static int mvneta_ethtool_set_wol(struct net_device *dev, } static int mvneta_ethtool_get_eee(struct net_device *dev, - struct ethtool_eee *eee) + struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); u32 lpi_ctl0; @@ -5113,7 +5113,7 @@ static int mvneta_ethtool_get_eee(struct net_device *dev, } static int mvneta_ethtool_set_eee(struct net_device *dev, - struct ethtool_eee *eee) + struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); u32 lpi_ctl0; diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index a2b3f4433ca8..8a6ae171e375 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1055,7 +1055,7 @@ static int lan743x_ethtool_get_ts_info(struct net_device *netdev, } static int lan743x_ethtool_get_eee(struct net_device *netdev, - struct ethtool_eee *eee) + struct ethtool_keee *eee) { struct lan743x_adapter *adapter = netdev_priv(netdev); struct phy_device *phydev = netdev->phydev; @@ -1092,7 +1092,7 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev, } static int lan743x_ethtool_set_eee(struct net_device *netdev, - struct ethtool_eee *eee) + struct ethtool_keee *eee) { struct lan743x_adapter *adapter; struct phy_device *phydev; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 0e240b5ab8d4..77491fb64039 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -1776,7 +1776,7 @@ static int qede_get_tunable(struct net_device *dev, return 0; } -static int qede_get_eee(struct net_device *dev, struct ethtool_eee *edata) +static int qede_get_eee(struct net_device *dev, struct ethtool_keee *edata) { struct qede_dev *edev = netdev_priv(dev); struct qed_link_output current_link; @@ -1810,7 +1810,7 @@ static int qede_get_eee(struct net_device *dev, struct ethtool_eee *edata) return 0; } -static int qede_set_eee(struct net_device *dev, struct ethtool_eee *edata) +static int qede_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct qede_dev *edev = netdev_priv(dev); struct qed_link_output current_link; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index dd73df6b17b0..3d30d4499791 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1974,7 +1974,7 @@ static int rtl_set_coalesce(struct net_device *dev, return 0; } -static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data) +static int rtl8169_get_eee(struct net_device *dev, struct ethtool_keee *data) { struct rtl8169_private *tp = netdev_priv(dev); @@ -1984,7 +1984,7 @@ static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data) return phy_ethtool_get_eee(tp->phydev, data); } -static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) +static int rtl8169_set_eee(struct net_device *dev, struct ethtool_keee *data) { struct rtl8169_private *tp = netdev_priv(dev); int ret; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 8ba017ec9849..d93b628b7046 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -133,7 +133,7 @@ static const struct sxgbe_stats sxgbe_gstrings_stats[] = { #define SXGBE_STATS_LEN ARRAY_SIZE(sxgbe_gstrings_stats) static int sxgbe_get_eee(struct net_device *dev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct sxgbe_priv_data *priv = netdev_priv(dev); @@ -148,7 +148,7 @@ static int sxgbe_get_eee(struct net_device *dev, } static int sxgbe_set_eee(struct net_device *dev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct sxgbe_priv_data *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 42d27b97dd1d..bbecb3b89535 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -852,7 +852,7 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) } static int stmmac_ethtool_op_get_eee(struct net_device *dev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct stmmac_priv *priv = netdev_priv(dev); @@ -868,7 +868,7 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev, } static int stmmac_ethtool_op_set_eee(struct net_device *dev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct stmmac_priv *priv = netdev_priv(dev); int ret; diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c index 35fceba01ea4..d6ce2c9f0a8d 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c +++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c @@ -514,14 +514,14 @@ am65_cpsw_set_link_ksettings(struct net_device *ndev, return phylink_ethtool_ksettings_set(salve->phylink, ecmd); } -static int am65_cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata) +static int am65_cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct am65_cpsw_slave_data *salve = am65_ndev_to_slave(ndev); return phylink_ethtool_get_eee(salve->phylink, edata); } -static int am65_cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata) +static int am65_cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct am65_cpsw_slave_data *salve = am65_ndev_to_slave(ndev); diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index a557a477d039..f7b283353ba2 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -422,7 +422,7 @@ int cpsw_set_link_ksettings(struct net_device *ndev, return phy_ethtool_ksettings_set(cpsw->slaves[slave_no].phy, ecmd); } -int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata) +int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; @@ -434,7 +434,7 @@ int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata) return -EOPNOTSUPP; } -int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata) +int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 0e27c433098d..7efa72502c86 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -496,8 +496,8 @@ int cpsw_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *ecmd); int cpsw_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *ecmd); -int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata); -int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata); +int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata); +int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata); int cpsw_nway_reset(struct net_device *ndev); void cpsw_get_ringparam(struct net_device *ndev, struct ethtool_ringparam *ering, diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c index a27ec1dcc8d5..9a7dd7efcf69 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c +++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c @@ -45,7 +45,7 @@ static int emac_set_link_ksettings(struct net_device *ndev, return phy_ethtool_set_link_ksettings(ndev, ecmd); } -static int emac_get_eee(struct net_device *ndev, struct ethtool_eee *edata) +static int emac_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { if (!ndev->phydev) return -EOPNOTSUPP; @@ -53,7 +53,7 @@ static int emac_get_eee(struct net_device *ndev, struct ethtool_eee *edata) return phy_ethtool_get_eee(ndev->phydev, edata); } -static int emac_set_eee(struct net_device *ndev, struct ethtool_eee *edata) +static int emac_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { if (!ndev->phydev) return -EOPNOTSUPP; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index eba652a4c1d8..1faa22f58366 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1461,7 +1461,7 @@ static int m88e1540_get_fld(struct phy_device *phydev, u8 *msecs) static int m88e1540_set_fld(struct phy_device *phydev, const u8 *msecs) { - struct ethtool_eee eee; + struct ethtool_keee eee; int val, ret; if (*msecs == ETHTOOL_PHY_FAST_LINK_DOWN_OFF) diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 747d14bf152c..adee5e712871 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -1443,13 +1443,13 @@ EXPORT_SYMBOL(genphy_c45_eee_is_active); /** * genphy_c45_ethtool_get_eee - get EEE supported and status * @phydev: target phy_device struct - * @data: ethtool_eee data + * @data: ethtool_keee data * * Description: it reports the Supported/Advertisement/LP Advertisement * capabilities. */ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, - struct ethtool_eee *data) + struct ethtool_keee *data) { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; __ETHTOOL_DECLARE_LINK_MODE_MASK(lp) = {}; @@ -1481,7 +1481,7 @@ EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); /** * genphy_c45_ethtool_set_eee - set EEE supported and status * @phydev: target phy_device struct - * @data: ethtool_eee data + * @data: ethtool_keee data * * Description: sets the Supported/Advertisement/LP Advertisement * capabilities. If eee_enabled is false, no links modes are @@ -1490,7 +1490,7 @@ EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); * non-destructive way. */ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, - struct ethtool_eee *data) + struct ethtool_keee *data) { int ret; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 3376e58e2b88..3b9531143be1 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1632,12 +1632,12 @@ EXPORT_SYMBOL(phy_get_eee_err); /** * phy_ethtool_get_eee - get EEE supported and status * @phydev: target phy_device struct - * @data: ethtool_eee data + * @data: ethtool_keee data * * Description: it reportes the Supported/Advertisement/LP Advertisement * capabilities. */ -int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data) +int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) { int ret; @@ -1655,11 +1655,11 @@ EXPORT_SYMBOL(phy_ethtool_get_eee); /** * phy_ethtool_set_eee - set EEE supported and status * @phydev: target phy_device struct - * @data: ethtool_eee data + * @data: ethtool_keee data * * Description: it is to program the Advertisement EEE register. */ -int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) +int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data) { int ret; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index ed0b4ccaa6a6..503fd7c40523 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2764,9 +2764,9 @@ EXPORT_SYMBOL_GPL(phylink_init_eee); /** * phylink_ethtool_get_eee() - read the energy efficient ethernet parameters * @pl: a pointer to a &struct phylink returned from phylink_create() - * @eee: a pointer to a &struct ethtool_eee for the read parameters + * @eee: a pointer to a &struct ethtool_keee for the read parameters */ -int phylink_ethtool_get_eee(struct phylink *pl, struct ethtool_eee *eee) +int phylink_ethtool_get_eee(struct phylink *pl, struct ethtool_keee *eee) { int ret = -EOPNOTSUPP; @@ -2782,9 +2782,9 @@ EXPORT_SYMBOL_GPL(phylink_ethtool_get_eee); /** * phylink_ethtool_set_eee() - set the energy efficient ethernet parameters * @pl: a pointer to a &struct phylink returned from phylink_create() - * @eee: a pointer to a &struct ethtool_eee for the desired parameters + * @eee: a pointer to a &struct ethtool_keee for the desired parameters */ -int phylink_ethtool_set_eee(struct phylink *pl, struct ethtool_eee *eee) +int phylink_ethtool_set_eee(struct phylink *pl, struct ethtool_keee *eee) { int ret = -EOPNOTSUPP; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index d837c1887416..3922a9afdd1f 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -667,7 +667,7 @@ static int ax88179_set_link_ksettings(struct net_device *net, } static int -ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_eee *data) +ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_keee *data) { int val; @@ -696,7 +696,7 @@ ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_eee *data) } static int -ax88179_ethtool_set_eee(struct usbnet *dev, struct ethtool_eee *data) +ax88179_ethtool_set_eee(struct usbnet *dev, struct ethtool_keee *data) { u16 tmp16 = ethtool_adv_to_mmd_eee_adv_t(data->advertised); @@ -807,7 +807,7 @@ static void ax88179_enable_eee(struct usbnet *dev) GMII_PHY_PAGE_SELECT, 2, &tmp16); } -static int ax88179_get_eee(struct net_device *net, struct ethtool_eee *edata) +static int ax88179_get_eee(struct net_device *net, struct ethtool_keee *edata) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; @@ -818,7 +818,7 @@ static int ax88179_get_eee(struct net_device *net, struct ethtool_eee *edata) return ax88179_ethtool_get_eee(dev, edata); } -static int ax88179_set_eee(struct net_device *net, struct ethtool_eee *edata) +static int ax88179_set_eee(struct net_device *net, struct ethtool_keee *edata) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; @@ -1587,7 +1587,7 @@ static int ax88179_reset(struct usbnet *dev) u16 *tmp16; u8 *tmp; struct ax88179_data *ax179_data = dev->driver_priv; - struct ethtool_eee eee_data; + struct ethtool_keee eee_data; tmp16 = (u16 *)buf; tmp = (u8 *)buf; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a6d653ff552a..106282612bc2 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1673,7 +1673,7 @@ static int lan78xx_set_wol(struct net_device *netdev, return ret; } -static int lan78xx_get_eee(struct net_device *net, struct ethtool_eee *edata) +static int lan78xx_get_eee(struct net_device *net, struct ethtool_keee *edata) { struct lan78xx_net *dev = netdev_priv(net); struct phy_device *phydev = net->phydev; @@ -1709,7 +1709,7 @@ exit: return ret; } -static int lan78xx_set_eee(struct net_device *net, struct ethtool_eee *edata) +static int lan78xx_set_eee(struct net_device *net, struct ethtool_keee *edata) { struct lan78xx_net *dev = netdev_priv(net); int ret; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0d0672d2a654..dc163b766a89 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -891,8 +891,8 @@ struct r8152 { void (*up)(struct r8152 *tp); void (*down)(struct r8152 *tp); void (*unload)(struct r8152 *tp); - int (*eee_get)(struct r8152 *tp, struct ethtool_eee *eee); - int (*eee_set)(struct r8152 *tp, struct ethtool_eee *eee); + int (*eee_get)(struct r8152 *tp, struct ethtool_keee *eee); + int (*eee_set)(struct r8152 *tp, struct ethtool_keee *eee); bool (*in_nway)(struct r8152 *tp); void (*hw_phy_cfg)(struct r8152 *tp); void (*autosuspend_en)(struct r8152 *tp, bool enable); @@ -8922,7 +8922,7 @@ static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data) } } -static int r8152_get_eee(struct r8152 *tp, struct ethtool_eee *eee) +static int r8152_get_eee(struct r8152 *tp, struct ethtool_keee *eee) { u32 lp, adv, supported = 0; u16 val; @@ -8945,7 +8945,7 @@ static int r8152_get_eee(struct r8152 *tp, struct ethtool_eee *eee) return 0; } -static int r8152_set_eee(struct r8152 *tp, struct ethtool_eee *eee) +static int r8152_set_eee(struct r8152 *tp, struct ethtool_keee *eee) { u16 val = ethtool_adv_to_mmd_eee_adv_t(eee->advertised); @@ -8957,7 +8957,7 @@ static int r8152_set_eee(struct r8152 *tp, struct ethtool_eee *eee) return 0; } -static int r8153_get_eee(struct r8152 *tp, struct ethtool_eee *eee) +static int r8153_get_eee(struct r8152 *tp, struct ethtool_keee *eee) { u32 lp, adv, supported = 0; u16 val; @@ -8981,7 +8981,7 @@ static int r8153_get_eee(struct r8152 *tp, struct ethtool_eee *eee) } static int -rtl_ethtool_get_eee(struct net_device *net, struct ethtool_eee *edata) +rtl_ethtool_get_eee(struct net_device *net, struct ethtool_keee *edata) { struct r8152 *tp = netdev_priv(net); int ret; @@ -9008,7 +9008,7 @@ out: } static int -rtl_ethtool_set_eee(struct net_device *net, struct ethtool_eee *edata) +rtl_ethtool_set_eee(struct net_device *net, struct ethtool_keee *edata) { struct r8152 *tp = netdev_priv(net); int ret; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 325e0778e937..a850bab8489f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -222,6 +222,18 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); +struct ethtool_keee { + u32 cmd; + u32 supported; + u32 advertised; + u32 lp_advertised; + u32 eee_active; + u32 eee_enabled; + u32 tx_lpi_enabled; + u32 tx_lpi_timer; + u32 reserved[2]; +}; + struct kernel_ethtool_coalesce { u8 use_cqe_mode_tx; u8 use_cqe_mode_rx; @@ -892,8 +904,8 @@ struct ethtool_ops { struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); - int (*get_eee)(struct net_device *, struct ethtool_eee *); - int (*set_eee)(struct net_device *, struct ethtool_eee *); + int (*get_eee)(struct net_device *dev, struct ethtool_keee *eee); + int (*set_eee)(struct net_device *dev, struct ethtool_keee *eee); int (*get_tunable)(struct net_device *, const struct ethtool_tunable *, void *); int (*set_tunable)(struct net_device *, diff --git a/include/linux/phy.h b/include/linux/phy.h index c9994a59ca2e..a66f07d3f5f4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1908,9 +1908,9 @@ int genphy_c45_plca_get_status(struct phy_device *phydev, int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, unsigned long *lp, bool *is_enabled); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, - struct ethtool_eee *data); + struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, - struct ethtool_eee *data); + struct ethtool_keee *data); int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); @@ -1988,8 +1988,8 @@ int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); -int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); -int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); +int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); +int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index d589f89c612c..6ba411732a0d 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -584,8 +584,8 @@ int phylink_ethtool_set_pauseparam(struct phylink *, struct ethtool_pauseparam *); int phylink_get_eee_err(struct phylink *); int phylink_init_eee(struct phylink *, bool); -int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); -int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); +int phylink_ethtool_get_eee(struct phylink *link, struct ethtool_keee *eee); +int phylink_ethtool_set_eee(struct phylink *link, struct ethtool_keee *eee); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); int phylink_speed_down(struct phylink *pl, bool sync); int phylink_speed_up(struct phylink *pl); diff --git a/include/net/dsa.h b/include/net/dsa.h index 82135fbdb1e6..7c0da9effe4e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -991,9 +991,9 @@ struct dsa_switch_ops { * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, - struct ethtool_eee *e); + struct ethtool_keee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, - struct ethtool_eee *e); + struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); diff --git a/net/dsa/user.c b/net/dsa/user.c index b15e71cc342c..e03da3a4ac38 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -1222,7 +1222,7 @@ static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) return ret; } -static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; @@ -1242,7 +1242,7 @@ static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_set_eee(dp->pl, e); } -static int dsa_user_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 2853394d06a8..21b0e845a531 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -5,7 +5,7 @@ #include "bitset.h" #define EEE_MODES_COUNT \ - (sizeof_field(struct ethtool_eee, supported) * BITS_PER_BYTE) + (sizeof_field(struct ethtool_keee, supported) * BITS_PER_BYTE) struct eee_req_info { struct ethnl_req_info base; @@ -13,7 +13,7 @@ struct eee_req_info { struct eee_reply_data { struct ethnl_reply_data base; - struct ethtool_eee eee; + struct ethtool_keee eee; }; #define EEE_REPDATA(__reply_base) \ @@ -48,7 +48,7 @@ static int eee_reply_size(const struct ethnl_req_info *req_base, { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); - const struct ethtool_eee *eee = &data->eee; + const struct ethtool_keee *eee = &data->eee; int len = 0; int ret; @@ -84,7 +84,7 @@ static int eee_fill_reply(struct sk_buff *skb, { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); - const struct ethtool_eee *eee = &data->eee; + const struct ethtool_keee *eee = &data->eee; int ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_OURS, @@ -132,7 +132,7 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; - struct ethtool_eee eee = {}; + struct ethtool_keee eee = {}; bool mod = false; int ret; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7519b0818b91..b02ca72f438e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1510,13 +1510,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_eee edata; + struct ethtool_keee edata; int rc; if (!dev->ethtool_ops->get_eee) return -EOPNOTSUPP; - memset(&edata, 0, sizeof(struct ethtool_eee)); + memset(&edata, 0, sizeof(struct ethtool_keee)); edata.cmd = ETHTOOL_GEEE; rc = dev->ethtool_ops->get_eee(dev, &edata); @@ -1531,7 +1531,7 @@ static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_eee edata; + struct ethtool_keee edata; int ret; if (!dev->ethtool_ops->set_eee) -- cgit v1.2.3 From 285cc15cc555b4f05ebf2556bc6e85a6d36b790a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jan 2024 14:26:50 +0100 Subject: ethtool: adjust struct ethtool_keee to kernel needs This patch changes the following in struct ethtool_keee - remove member cmd, it's not needed on kernel side - remove reserved fields - switch the semantically boolean members to type bool We don't have to change any user of the boolean members due to the implicit casting from/to bool. A small change is needed where a pointer to bool members is used, in addition remove few now unneeded double negations. Reviewed-by: Andrew Lunn Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/ethtool.h | 8 +++----- net/ethtool/eee.c | 12 ++++++------ 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a850bab8489f..14549cb9e2b2 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -223,15 +223,13 @@ __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); struct ethtool_keee { - u32 cmd; u32 supported; u32 advertised; u32 lp_advertised; - u32 eee_active; - u32 eee_enabled; - u32 tx_lpi_enabled; u32 tx_lpi_timer; - u32 reserved[2]; + bool tx_lpi_enabled; + bool eee_active; + bool eee_enabled; }; struct kernel_ethtool_coalesce { diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 21b0e845a531..ac9f694ffe20 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -98,10 +98,10 @@ static int eee_fill_reply(struct sk_buff *skb, if (ret < 0) return ret; - if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, !!eee->eee_active) || - nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, !!eee->eee_enabled) || + if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, eee->eee_active) || + nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, eee->eee_enabled) || nla_put_u8(skb, ETHTOOL_A_EEE_TX_LPI_ENABLED, - !!eee->tx_lpi_enabled) || + eee->tx_lpi_enabled) || nla_put_u32(skb, ETHTOOL_A_EEE_TX_LPI_TIMER, eee->tx_lpi_timer)) return -EMSGSIZE; @@ -145,9 +145,9 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) link_mode_names, info->extack, &mod); if (ret < 0) return ret; - ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); - ethnl_update_bool32(&eee.tx_lpi_enabled, - tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod); + ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); + ethnl_update_bool(&eee.tx_lpi_enabled, tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], + &mod); ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], &mod); if (!mod) -- cgit v1.2.3 From 1d756ff13da6a2222ac4387511f2a0e2e83ce670 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jan 2024 14:28:47 +0100 Subject: ethtool: add suffix _u32 to legacy bitmap members of struct ethtool_keee This is in preparation of using the existing names for linkmode bitmaps. Suggested-by: Andrew Lunn Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- .../net/ethernet/aquantia/atlantic/aq_ethtool.c | 8 +++---- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 8 +++---- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 +++++----- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 14 +++++------ drivers/net/ethernet/broadcom/tg3.c | 22 ++++++++--------- drivers/net/ethernet/intel/e1000e/ethtool.c | 10 ++++---- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 10 ++++---- drivers/net/ethernet/intel/igb/igb_ethtool.c | 20 ++++++++-------- drivers/net/ethernet/intel/igc/igc_ethtool.c | 12 +++++----- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 18 +++++++------- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 28 +++++++++++----------- drivers/net/phy/phy-c45.c | 12 +++++----- drivers/net/usb/ax88179_178a.c | 10 ++++---- drivers/net/usb/r8152.c | 14 +++++------ include/linux/ethtool.h | 6 ++--- net/ethtool/eee.c | 16 ++++++------- net/ethtool/ioctl.c | 12 +++++----- 17 files changed, 116 insertions(+), 116 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index be865776de55..0bd1a0a1ae6a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -713,14 +713,14 @@ static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_keee *eee) if (err < 0) return err; - eee->supported = eee_mask_to_ethtool_mask(supported_rates); + eee->supported_u32 = eee_mask_to_ethtool_mask(supported_rates); if (aq_nic->aq_nic_cfg.eee_speeds) - eee->advertised = eee->supported; + eee->advertised_u32 = eee->supported_u32; - eee->lp_advertised = eee_mask_to_ethtool_mask(rate); + eee->lp_advertised_u32 = eee_mask_to_ethtool_mask(rate); - eee->eee_enabled = !!eee->advertised; + eee->eee_enabled = !!eee->advertised_u32; eee->tx_lpi_enabled = eee->eee_enabled; if ((supported_rates & rate) & AQ_NIC_RATE_EEE_MSK) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 12d2785eeb8a..5f0e1759d078 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2120,14 +2120,14 @@ static int bnx2x_get_eee(struct net_device *dev, struct ethtool_keee *edata) eee_cfg = bp->link_vars.eee_status; - edata->supported = + edata->supported_u32 = bnx2x_eee_to_adv((eee_cfg & SHMEM_EEE_SUPPORTED_MASK) >> SHMEM_EEE_SUPPORTED_SHIFT); - edata->advertised = + edata->advertised_u32 = bnx2x_eee_to_adv((eee_cfg & SHMEM_EEE_ADV_STATUS_MASK) >> SHMEM_EEE_ADV_STATUS_SHIFT); - edata->lp_advertised = + edata->lp_advertised_u32 = bnx2x_eee_to_adv((eee_cfg & SHMEM_EEE_LP_ADV_STATUS_MASK) >> SHMEM_EEE_LP_ADV_STATUS_SHIFT); @@ -2162,7 +2162,7 @@ static int bnx2x_set_eee(struct net_device *dev, struct ethtool_keee *edata) return -EOPNOTSUPP; } - advertised = bnx2x_adv_to_eee(edata->advertised, + advertised = bnx2x_adv_to_eee(edata->advertised_u32, SHMEM_EEE_ADV_STATUS_SHIFT); if ((advertised != (eee_cfg & SHMEM_EEE_ADV_STATUS_MASK))) { DP(BNX2X_MSG_ETHTOOL, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d7626c26f9a9..fde32b32fa81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10624,7 +10624,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) struct ethtool_keee *eee = &bp->eee; u16 fw_speeds = le16_to_cpu(resp->supported_speeds_eee_mode); - eee->supported = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); + eee->supported_u32 = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); bp->lpi_tmr_lo = le32_to_cpu(resp->tx_lpi_timer_low) & PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_MASK; bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) & @@ -10775,7 +10775,7 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state) eee->eee_active = 1; fw_speeds = le16_to_cpu( resp->link_partner_adv_eee_link_speed_mask); - eee->lp_advertised = + eee->lp_advertised_u32 = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); } @@ -10786,7 +10786,7 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state) eee->eee_enabled = 1; fw_speeds = le16_to_cpu(resp->adv_eee_link_speed_mask); - eee->advertised = + eee->advertised_u32 = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); if (resp->eee_config_phy_addr & @@ -10969,7 +10969,7 @@ static void bnxt_hwrm_set_eee(struct bnxt *bp, flags |= PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE; req->flags |= cpu_to_le32(flags); - eee_speeds = bnxt_get_fw_auto_link_speeds(eee->advertised); + eee_speeds = bnxt_get_fw_auto_link_speeds(eee->advertised_u32); req->eee_link_speed_mask = cpu_to_le16(eee_speeds); req->tx_lpi_timer = cpu_to_le32(eee->tx_lpi_timer); } else { @@ -11336,8 +11336,8 @@ static bool bnxt_eee_config_ok(struct bnxt *bp) eee->eee_enabled = 0; return false; } - if (eee->advertised & ~advertising) { - eee->advertised = advertising & eee->supported; + if (eee->advertised_u32 & ~advertising) { + eee->advertised_u32 = advertising & eee->supported_u32; return false; } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d6a8577d68af..481b835a7703 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3919,16 +3919,16 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_keee *edata) edata->tx_lpi_timer = eee->tx_lpi_timer; } } - if (!edata->advertised) { - edata->advertised = advertising & eee->supported; - } else if (edata->advertised & ~advertising) { + if (!edata->advertised_u32) { + edata->advertised_u32 = advertising & eee->supported_u32; + } else if (edata->advertised_u32 & ~advertising) { netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n", - edata->advertised, advertising); + edata->advertised_u32, advertising); rc = -EINVAL; goto eee_exit; } - eee->advertised = edata->advertised; + eee->advertised_u32 = edata->advertised_u32; eee->tx_lpi_enabled = edata->tx_lpi_enabled; eee->tx_lpi_timer = edata->tx_lpi_timer; eee_ok: @@ -3954,12 +3954,12 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata) /* Preserve tx_lpi_timer so that the last value will be used * by default when it is re-enabled. */ - edata->advertised = 0; + edata->advertised_u32 = 0; edata->tx_lpi_enabled = 0; } if (!bp->eee.eee_active) - edata->lp_advertised = 0; + edata->lp_advertised_u32 = 0; return 0; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 11054177c2ec..f644a91317c9 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -2362,13 +2362,13 @@ static void tg3_eee_pull_config(struct tg3 *tp, struct ethtool_keee *eee) /* Pull lp advertised settings */ if (tg3_phy_cl45_read(tp, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE, &val)) return; - dest->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val); + dest->lp_advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(val); /* Pull advertised and eee_enabled settings */ if (tg3_phy_cl45_read(tp, MDIO_MMD_AN, MDIO_AN_EEE_ADV, &val)) return; dest->eee_enabled = !!val; - dest->advertised = mmd_eee_adv_to_ethtool_adv_t(val); + dest->advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(val); /* Pull tx_lpi_enabled */ val = tr32(TG3_CPMU_EEE_MODE); @@ -4364,9 +4364,9 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) if (!tp->eee.eee_enabled) { val = 0; - tp->eee.advertised = 0; + tp->eee.advertised_u32 = 0; } else { - tp->eee.advertised = advertise & + tp->eee.advertised_u32 = advertise & (ADVERTISED_100baseT_Full | ADVERTISED_1000baseT_Full); } @@ -4626,13 +4626,13 @@ static bool tg3_phy_eee_config_ok(struct tg3 *tp) tg3_eee_pull_config(tp, &eee); if (tp->eee.eee_enabled) { - if (tp->eee.advertised != eee.advertised || + if (tp->eee.advertised_u32 != eee.advertised_u32 || tp->eee.tx_lpi_timer != eee.tx_lpi_timer || tp->eee.tx_lpi_enabled != eee.tx_lpi_enabled) return false; } else { /* EEE is disabled but we're advertising */ - if (eee.advertised) + if (eee.advertised_u32) return false; } @@ -14189,7 +14189,7 @@ static int tg3_set_eee(struct net_device *dev, struct ethtool_keee *edata) return -EOPNOTSUPP; } - if (edata->advertised != tp->eee.advertised) { + if (edata->advertised_u32 != tp->eee.advertised_u32) { netdev_warn(tp->dev, "Direct manipulation of EEE advertisement is not supported\n"); return -EINVAL; @@ -15655,10 +15655,10 @@ static int tg3_phy_probe(struct tg3 *tp) tg3_chip_rev_id(tp) != CHIPREV_ID_57765_A0))) { tp->phy_flags |= TG3_PHYFLG_EEE_CAP; - tp->eee.supported = SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Full; - tp->eee.advertised = ADVERTISED_100baseT_Full | - ADVERTISED_1000baseT_Full; + tp->eee.supported_u32 = SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full; + tp->eee.advertised_u32 = ADVERTISED_100baseT_Full | + ADVERTISED_1000baseT_Full; tp->eee.eee_enabled = 1; tp->eee.tx_lpi_enabled = 1; tp->eee.tx_lpi_timer = TG3_CPMU_DBTMR1_LNKIDLE_2047US; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 343f54b2b6ae..ff243ae71b78 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -2223,16 +2223,16 @@ static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) ret_val = e1000_read_emi_reg_locked(hw, cap_addr, &phy_data); if (ret_val) goto release; - edata->supported = mmd_eee_cap_to_ethtool_sup_t(phy_data); + edata->supported_u32 = mmd_eee_cap_to_ethtool_sup_t(phy_data); /* EEE Advertised */ - edata->advertised = mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); + edata->advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); /* EEE Link Partner Advertised */ ret_val = e1000_read_emi_reg_locked(hw, lpa_addr, &phy_data); if (ret_val) goto release; - edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data); + edata->lp_advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(phy_data); /* EEE PCS Status */ ret_val = e1000_read_emi_reg_locked(hw, pcs_stat_addr, &phy_data); @@ -2283,12 +2283,12 @@ static int e1000e_set_eee(struct net_device *netdev, struct ethtool_keee *edata) return -EINVAL; } - if (edata->advertised & ~(ADVERTISE_100_FULL | ADVERTISE_1000_FULL)) { + if (edata->advertised_u32 & ~(ADVERTISE_100_FULL | ADVERTISE_1000_FULL)) { e_err("EEE advertisement supports only 100TX and/or 1000T full-duplex\n"); return -EINVAL; } - adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); + adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised_u32); hw->dev_spec.ich8lan.eee_disable = !edata->eee_enabled; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 9dfda3c48af3..1b5473358e1a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5664,16 +5664,16 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) if (phy_cfg.eee_capability == 0) return -EOPNOTSUPP; - edata->supported = SUPPORTED_Autoneg; - edata->lp_advertised = edata->supported; + edata->supported_u32 = SUPPORTED_Autoneg; + edata->lp_advertised_u32 = edata->supported_u32; /* Get current configuration */ status = i40e_aq_get_phy_capabilities(hw, false, false, &phy_cfg, NULL); if (status) return -EAGAIN; - edata->advertised = phy_cfg.eee_capability ? SUPPORTED_Autoneg : 0U; - edata->eee_enabled = !!edata->advertised; + edata->advertised_u32 = phy_cfg.eee_capability ? SUPPORTED_Autoneg : 0U; + edata->eee_enabled = !!edata->advertised_u32; edata->tx_lpi_enabled = pf->stats.tx_lpi_status; edata->eee_active = pf->stats.tx_lpi_status && pf->stats.rx_lpi_status; @@ -5691,7 +5691,7 @@ static int i40e_is_eee_param_supported(struct net_device *netdev, u32 value; const char *name; } param[] = { - {edata->advertised & ~SUPPORTED_Autoneg, "advertise"}, + {edata->advertised_u32 & ~SUPPORTED_Autoneg, "advertise"}, {edata->tx_lpi_timer, "tx-timer"}, {edata->tx_lpi_enabled != pf->stats.tx_lpi_status, "tx-lpi"} }; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 778d1e6cfc45..b87b23d2151c 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -3038,10 +3038,10 @@ static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata) (hw->phy.media_type != e1000_media_type_copper)) return -EOPNOTSUPP; - edata->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full); + edata->supported_u32 = (SUPPORTED_1000baseT_Full | + SUPPORTED_100baseT_Full); if (!hw->dev_spec._82575.eee_disable) - edata->advertised = + edata->advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); /* The IPCNFG and EEER registers are not supported on I354. */ @@ -3068,7 +3068,7 @@ static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata) if (ret_val) return -ENODATA; - edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data); + edata->lp_advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(phy_data); break; case e1000_i354: case e1000_i210: @@ -3079,7 +3079,7 @@ static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata) if (ret_val) return -ENODATA; - edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data); + edata->lp_advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(phy_data); break; default: @@ -3099,7 +3099,7 @@ static int igb_get_eee(struct net_device *netdev, struct ethtool_keee *edata) edata->eee_enabled = false; edata->eee_active = false; edata->tx_lpi_enabled = false; - edata->advertised &= ~edata->advertised; + edata->advertised_u32 &= ~edata->advertised_u32; } return 0; @@ -3138,14 +3138,14 @@ static int igb_set_eee(struct net_device *netdev, return -EINVAL; } - if (!edata->advertised || (edata->advertised & + if (!edata->advertised_u32 || (edata->advertised_u32 & ~(ADVERTISE_100_FULL | ADVERTISE_1000_FULL))) { dev_err(&adapter->pdev->dev, "EEE Advertisement supports only 100Tx and/or 100T full duplex\n"); return -EINVAL; } - adv100m_eee = !!(edata->advertised & ADVERTISE_100_FULL); - adv1g_eee = !!(edata->advertised & ADVERTISE_1000_FULL); + adv100m_eee = !!(edata->advertised_u32 & ADVERTISE_100_FULL); + adv1g_eee = !!(edata->advertised_u32 & ADVERTISE_1000_FULL); } else if (!edata->eee_enabled) { dev_err(&adapter->pdev->dev, @@ -3153,7 +3153,7 @@ static int igb_set_eee(struct net_device *netdev, return -EINVAL; } - adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); + adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised_u32); if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) { hw->dev_spec._82575.eee_disable = !edata->eee_enabled; adapter->flags |= IGB_FLAG_EEE; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index f2dcfe920f4f..7f844e967421 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1630,11 +1630,11 @@ static int igc_ethtool_get_eee(struct net_device *netdev, u32 eeer; if (hw->dev_spec._base.eee_enable) - edata->advertised = + edata->advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); *edata = adapter->eee; - edata->supported = SUPPORTED_Autoneg; + edata->supported_u32 = SUPPORTED_Autoneg; eeer = rd32(IGC_EEER); @@ -1647,8 +1647,8 @@ static int igc_ethtool_get_eee(struct net_device *netdev, edata->eee_enabled = hw->dev_spec._base.eee_enable; - edata->advertised = SUPPORTED_Autoneg; - edata->lp_advertised = SUPPORTED_Autoneg; + edata->advertised_u32 = SUPPORTED_Autoneg; + edata->lp_advertised_u32 = SUPPORTED_Autoneg; /* Report correct negotiated EEE status for devices that * wrongly report EEE at half-duplex @@ -1657,7 +1657,7 @@ static int igc_ethtool_get_eee(struct net_device *netdev, edata->eee_enabled = false; edata->eee_active = false; edata->tx_lpi_enabled = false; - edata->advertised &= ~edata->advertised; + edata->advertised_u32 &= ~edata->advertised_u32; } return 0; @@ -1699,7 +1699,7 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return -EINVAL; } - adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); + adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised_u32); if (hw->dev_spec._base.eee_enable != edata->eee_enabled) { hw->dev_spec._base.eee_enable = edata->eee_enabled; adapter->flags |= IGC_FLAG_EEE; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 0aa73519a29d..ca69a8221793 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3436,27 +3436,27 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata) if (rc) return rc; - edata->lp_advertised = 0; + edata->lp_advertised_u32 = 0; for (i = 0; i < ARRAY_SIZE(ixgbe_lp_map); ++i) { if (info[0] & ixgbe_lp_map[i].lp_advertised) - edata->lp_advertised |= ixgbe_lp_map[i].mac_speed; + edata->lp_advertised_u32 |= ixgbe_lp_map[i].mac_speed; } - edata->supported = 0; + edata->supported_u32 = 0; for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed) - edata->supported |= ixgbe_ls_map[i].supported; + edata->supported_u32 |= ixgbe_ls_map[i].supported; } - edata->advertised = 0; + edata->advertised_u32 = 0; for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed) - edata->advertised |= ixgbe_ls_map[i].supported; + edata->advertised_u32 |= ixgbe_ls_map[i].supported; } - edata->eee_enabled = !!edata->advertised; + edata->eee_enabled = !!edata->advertised_u32; edata->tx_lpi_enabled = edata->eee_enabled; - if (edata->advertised & edata->lp_advertised) + if (edata->advertised_u32 & edata->lp_advertised_u32) edata->eee_active = true; return 0; @@ -3504,7 +3504,7 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata) return -EINVAL; } - if (eee_data.advertised != edata->advertised) { + if (eee_data.advertised_u32 != edata->advertised_u32) { e_err(drv, "Setting EEE advertised speeds is not supported\n"); return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 77491fb64039..dfa15619fd78 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -1790,17 +1790,17 @@ static int qede_get_eee(struct net_device *dev, struct ethtool_keee *edata) } if (current_link.eee.adv_caps & QED_EEE_1G_ADV) - edata->advertised = ADVERTISED_1000baseT_Full; + edata->advertised_u32 = ADVERTISED_1000baseT_Full; if (current_link.eee.adv_caps & QED_EEE_10G_ADV) - edata->advertised |= ADVERTISED_10000baseT_Full; + edata->advertised_u32 |= ADVERTISED_10000baseT_Full; if (current_link.sup_caps & QED_EEE_1G_ADV) - edata->supported = ADVERTISED_1000baseT_Full; + edata->supported_u32 = ADVERTISED_1000baseT_Full; if (current_link.sup_caps & QED_EEE_10G_ADV) - edata->supported |= ADVERTISED_10000baseT_Full; + edata->supported_u32 |= ADVERTISED_10000baseT_Full; if (current_link.eee.lp_adv_caps & QED_EEE_1G_ADV) - edata->lp_advertised = ADVERTISED_1000baseT_Full; + edata->lp_advertised_u32 = ADVERTISED_1000baseT_Full; if (current_link.eee.lp_adv_caps & QED_EEE_10G_ADV) - edata->lp_advertised |= ADVERTISED_10000baseT_Full; + edata->lp_advertised_u32 |= ADVERTISED_10000baseT_Full; edata->tx_lpi_timer = current_link.eee.tx_lpi_timer; edata->eee_enabled = current_link.eee.enable; @@ -1832,20 +1832,20 @@ static int qede_set_eee(struct net_device *dev, struct ethtool_keee *edata) memset(¶ms, 0, sizeof(params)); params.override_flags |= QED_LINK_OVERRIDE_EEE_CONFIG; - if (!(edata->advertised & (ADVERTISED_1000baseT_Full | - ADVERTISED_10000baseT_Full)) || - ((edata->advertised & (ADVERTISED_1000baseT_Full | - ADVERTISED_10000baseT_Full)) != - edata->advertised)) { + if (!(edata->advertised_u32 & (ADVERTISED_1000baseT_Full | + ADVERTISED_10000baseT_Full)) || + ((edata->advertised_u32 & (ADVERTISED_1000baseT_Full | + ADVERTISED_10000baseT_Full)) != + edata->advertised_u32)) { DP_VERBOSE(edev, QED_MSG_DEBUG, "Invalid advertised capabilities %d\n", - edata->advertised); + edata->advertised_u32); return -EINVAL; } - if (edata->advertised & ADVERTISED_1000baseT_Full) + if (edata->advertised_u32 & ADVERTISED_1000baseT_Full) params.eee.adv_caps = QED_EEE_1G_ADV; - if (edata->advertised & ADVERTISED_10000baseT_Full) + if (edata->advertised_u32 & ADVERTISED_10000baseT_Full) params.eee.adv_caps |= QED_EEE_10G_ADV; params.eee.enable = edata->eee_enabled; params.eee.tx_lpi_enable = edata->tx_lpi_enabled; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index adee5e712871..99c84af25746 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -1463,12 +1463,12 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, data->eee_enabled = is_enabled; data->eee_active = ret; - if (!ethtool_convert_link_mode_to_legacy_u32(&data->supported, + if (!ethtool_convert_link_mode_to_legacy_u32(&data->supported_u32, phydev->supported_eee)) overflow = true; - if (!ethtool_convert_link_mode_to_legacy_u32(&data->advertised, adv)) + if (!ethtool_convert_link_mode_to_legacy_u32(&data->advertised_u32, adv)) overflow = true; - if (!ethtool_convert_link_mode_to_legacy_u32(&data->lp_advertised, lp)) + if (!ethtool_convert_link_mode_to_legacy_u32(&data->lp_advertised_u32, lp)) overflow = true; if (overflow) @@ -1495,11 +1495,11 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, int ret; if (data->eee_enabled) { - if (data->advertised) { + if (data->advertised_u32) { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv); ethtool_convert_legacy_u32_to_link_mode(adv, - data->advertised); + data->advertised_u32); linkmode_andnot(adv, adv, phydev->supported_eee); if (!linkmode_empty(adv)) { phydev_warn(phydev, "At least some EEE link modes are not supported.\n"); @@ -1507,7 +1507,7 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, } ethtool_convert_legacy_u32_to_link_mode(phydev->advertising_eee, - data->advertised); + data->advertised_u32); } else { linkmode_copy(phydev->advertising_eee, phydev->supported_eee); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 3922a9afdd1f..d6168eaa286f 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -676,21 +676,21 @@ ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_keee *data) MDIO_MMD_PCS); if (val < 0) return val; - data->supported = mmd_eee_cap_to_ethtool_sup_t(val); + data->supported_u32 = mmd_eee_cap_to_ethtool_sup_t(val); /* Get advertisement EEE */ val = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_ADV, MDIO_MMD_AN); if (val < 0) return val; - data->advertised = mmd_eee_adv_to_ethtool_adv_t(val); + data->advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(val); /* Get LP advertisement EEE */ val = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN); if (val < 0) return val; - data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val); + data->lp_advertised_u32 = mmd_eee_adv_to_ethtool_adv_t(val); return 0; } @@ -698,7 +698,7 @@ ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_keee *data) static int ax88179_ethtool_set_eee(struct usbnet *dev, struct ethtool_keee *data) { - u16 tmp16 = ethtool_adv_to_mmd_eee_adv_t(data->advertised); + u16 tmp16 = ethtool_adv_to_mmd_eee_adv_t(data->advertised_u32); return ax88179_phy_write_mmd_indirect(dev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, tmp16); @@ -1663,7 +1663,7 @@ static int ax88179_reset(struct usbnet *dev) ax88179_disable_eee(dev); ax88179_ethtool_get_eee(dev, &eee_data); - eee_data.advertised = 0; + eee_data.advertised_u32 = 0; ax88179_ethtool_set_eee(dev, &eee_data); /* Restart autoneg */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index dc163b766a89..3d806b3ff425 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8938,16 +8938,16 @@ static int r8152_get_eee(struct r8152 *tp, struct ethtool_keee *eee) eee->eee_enabled = tp->eee_en; eee->eee_active = !!(supported & adv & lp); - eee->supported = supported; - eee->advertised = tp->eee_adv; - eee->lp_advertised = lp; + eee->supported_u32 = supported; + eee->advertised_u32 = tp->eee_adv; + eee->lp_advertised_u32 = lp; return 0; } static int r8152_set_eee(struct r8152 *tp, struct ethtool_keee *eee) { - u16 val = ethtool_adv_to_mmd_eee_adv_t(eee->advertised); + u16 val = ethtool_adv_to_mmd_eee_adv_t(eee->advertised_u32); tp->eee_en = eee->eee_enabled; tp->eee_adv = val; @@ -8973,9 +8973,9 @@ static int r8153_get_eee(struct r8152 *tp, struct ethtool_keee *eee) eee->eee_enabled = tp->eee_en; eee->eee_active = !!(supported & adv & lp); - eee->supported = supported; - eee->advertised = tp->eee_adv; - eee->lp_advertised = lp; + eee->supported_u32 = supported; + eee->advertised_u32 = tp->eee_adv; + eee->lp_advertised_u32 = lp; return 0; } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 14549cb9e2b2..89807c30f5a7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -223,9 +223,9 @@ __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); struct ethtool_keee { - u32 supported; - u32 advertised; - u32 lp_advertised; + u32 supported_u32; + u32 advertised_u32; + u32 lp_advertised_u32; u32 tx_lpi_timer; bool tx_lpi_enabled; bool eee_active; diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index ac9f694ffe20..ca56f28173d5 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -5,7 +5,7 @@ #include "bitset.h" #define EEE_MODES_COUNT \ - (sizeof_field(struct ethtool_keee, supported) * BITS_PER_BYTE) + (sizeof_field(struct ethtool_keee, supported_u32) * BITS_PER_BYTE) struct eee_req_info { struct ethnl_req_info base; @@ -52,19 +52,19 @@ static int eee_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; - BUILD_BUG_ON(sizeof(eee->advertised) * BITS_PER_BYTE != + BUILD_BUG_ON(sizeof(eee->advertised_u32) * BITS_PER_BYTE != EEE_MODES_COUNT); - BUILD_BUG_ON(sizeof(eee->lp_advertised) * BITS_PER_BYTE != + BUILD_BUG_ON(sizeof(eee->lp_advertised_u32) * BITS_PER_BYTE != EEE_MODES_COUNT); /* MODES_OURS */ - ret = ethnl_bitset32_size(&eee->advertised, &eee->supported, + ret = ethnl_bitset32_size(&eee->advertised_u32, &eee->supported_u32, EEE_MODES_COUNT, link_mode_names, compact); if (ret < 0) return ret; len += ret; /* MODES_PEERS */ - ret = ethnl_bitset32_size(&eee->lp_advertised, NULL, + ret = ethnl_bitset32_size(&eee->lp_advertised_u32, NULL, EEE_MODES_COUNT, link_mode_names, compact); if (ret < 0) return ret; @@ -88,12 +88,12 @@ static int eee_fill_reply(struct sk_buff *skb, int ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_OURS, - &eee->advertised, &eee->supported, + &eee->advertised_u32, &eee->supported_u32, EEE_MODES_COUNT, link_mode_names, compact); if (ret < 0) return ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_PEER, - &eee->lp_advertised, NULL, EEE_MODES_COUNT, + &eee->lp_advertised_u32, NULL, EEE_MODES_COUNT, link_mode_names, compact); if (ret < 0) return ret; @@ -140,7 +140,7 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) if (ret < 0) return ret; - ret = ethnl_update_bitset32(&eee.advertised, EEE_MODES_COUNT, + ret = ethnl_update_bitset32(&eee.advertised_u32, EEE_MODES_COUNT, tb[ETHTOOL_A_EEE_MODES_OURS], link_mode_names, info->extack, &mod); if (ret < 0) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 46c29b369aeb..5b2ca72e3203 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1513,9 +1513,9 @@ static void eee_to_keee(struct ethtool_keee *keee, { memset(keee, 0, sizeof(*keee)); - keee->supported = eee->supported; - keee->advertised = eee->advertised; - keee->lp_advertised = eee->lp_advertised; + keee->supported_u32 = eee->supported; + keee->advertised_u32 = eee->advertised; + keee->lp_advertised_u32 = eee->lp_advertised; keee->eee_active = eee->eee_active; keee->eee_enabled = eee->eee_enabled; keee->tx_lpi_enabled = eee->tx_lpi_enabled; @@ -1527,9 +1527,9 @@ static void keee_to_eee(struct ethtool_eee *eee, { memset(eee, 0, sizeof(*eee)); - eee->supported = keee->supported; - eee->advertised = keee->advertised; - eee->lp_advertised = keee->lp_advertised; + eee->supported = keee->supported_u32; + eee->advertised = keee->advertised_u32; + eee->lp_advertised = keee->lp_advertised_u32; eee->eee_active = keee->eee_active; eee->eee_enabled = keee->eee_enabled; eee->tx_lpi_enabled = keee->tx_lpi_enabled; -- cgit v1.2.3 From 1f069de63602e8d39d7d9fd6195f65235316f79a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 27 Jan 2024 14:29:33 +0100 Subject: ethtool: add linkmode bitmap support to struct ethtool_keee Add linkmode bitmap members to struct ethtool_keee, but keep the legacy u32 bitmaps for compatibility with existing drivers. Use linkmode "supported" not being empty as indicator that a user wants to use the linkmode bitmap members instead of the legacy bitmaps. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 +++ net/ethtool/common.c | 5 +++++ net/ethtool/common.h | 1 + net/ethtool/eee.c | 49 +++++++++++++++++++++++++++++++++++-------------- net/ethtool/ioctl.c | 27 ++++++++++++++++++++++++--- 5 files changed, 68 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 89807c30f5a7..b90c33607594 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -223,6 +223,9 @@ __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); struct ethtool_keee { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertised); u32 supported_u32; u32 advertised_u32; u32 lp_advertised_u32; diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6b2a360dcdf0..ce486cec346c 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -712,3 +712,8 @@ ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) } } EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); + +bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee) +{ + return !linkmode_empty(eee->supported); +} diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 28b8aaaf9bcb..0f2b5f7eacee 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -55,5 +55,6 @@ int ethtool_get_module_eeprom_call(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data); bool __ethtool_dev_mm_supported(struct net_device *dev); +bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee); #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index ca56f28173d5..db6faa18fe41 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -30,6 +30,7 @@ static int eee_prepare_data(const struct ethnl_req_info *req_base, { struct eee_reply_data *data = EEE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct ethtool_keee *eee = &data->eee; int ret; if (!dev->ethtool_ops->get_eee) @@ -37,9 +38,18 @@ static int eee_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = dev->ethtool_ops->get_eee(dev, &data->eee); + ret = dev->ethtool_ops->get_eee(dev, eee); ethnl_ops_complete(dev); + if (!ret && !ethtool_eee_use_linkmodes(eee)) { + ethtool_convert_legacy_u32_to_link_mode(eee->supported, + eee->supported_u32); + ethtool_convert_legacy_u32_to_link_mode(eee->advertised, + eee->advertised_u32); + ethtool_convert_legacy_u32_to_link_mode(eee->lp_advertised, + eee->lp_advertised_u32); + } + return ret; } @@ -58,14 +68,16 @@ static int eee_reply_size(const struct ethnl_req_info *req_base, EEE_MODES_COUNT); /* MODES_OURS */ - ret = ethnl_bitset32_size(&eee->advertised_u32, &eee->supported_u32, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_bitset_size(eee->advertised, eee->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; len += ret; /* MODES_PEERS */ - ret = ethnl_bitset32_size(&eee->lp_advertised_u32, NULL, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_bitset_size(eee->lp_advertised, NULL, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; len += ret; @@ -87,14 +99,16 @@ static int eee_fill_reply(struct sk_buff *skb, const struct ethtool_keee *eee = &data->eee; int ret; - ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_OURS, - &eee->advertised_u32, &eee->supported_u32, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_OURS, + eee->advertised, eee->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; - ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_PEER, - &eee->lp_advertised_u32, NULL, EEE_MODES_COUNT, - link_mode_names, compact); + ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_PEER, + eee->lp_advertised, NULL, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; @@ -140,9 +154,16 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) if (ret < 0) return ret; - ret = ethnl_update_bitset32(&eee.advertised_u32, EEE_MODES_COUNT, - tb[ETHTOOL_A_EEE_MODES_OURS], - link_mode_names, info->extack, &mod); + if (ethtool_eee_use_linkmodes(&eee)) { + ret = ethnl_update_bitset(eee.advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS, + tb[ETHTOOL_A_EEE_MODES_OURS], + link_mode_names, info->extack, &mod); + } else { + ret = ethnl_update_bitset32(&eee.advertised_u32, EEE_MODES_COUNT, + tb[ETHTOOL_A_EEE_MODES_OURS], + link_mode_names, info->extack, &mod); + } if (ret < 0) return ret; ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 5b2ca72e3203..1763e8b697e1 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1520,6 +1520,13 @@ static void eee_to_keee(struct ethtool_keee *keee, keee->eee_enabled = eee->eee_enabled; keee->tx_lpi_enabled = eee->tx_lpi_enabled; keee->tx_lpi_timer = eee->tx_lpi_timer; + + ethtool_convert_legacy_u32_to_link_mode(keee->supported, + eee->supported); + ethtool_convert_legacy_u32_to_link_mode(keee->advertised, + eee->advertised); + ethtool_convert_legacy_u32_to_link_mode(keee->lp_advertised, + eee->lp_advertised); } static void keee_to_eee(struct ethtool_eee *eee, @@ -1527,13 +1534,27 @@ static void keee_to_eee(struct ethtool_eee *eee, { memset(eee, 0, sizeof(*eee)); - eee->supported = keee->supported_u32; - eee->advertised = keee->advertised_u32; - eee->lp_advertised = keee->lp_advertised_u32; eee->eee_active = keee->eee_active; eee->eee_enabled = keee->eee_enabled; eee->tx_lpi_enabled = keee->tx_lpi_enabled; eee->tx_lpi_timer = keee->tx_lpi_timer; + + if (ethtool_eee_use_linkmodes(keee)) { + bool overflow; + + overflow = !ethtool_convert_link_mode_to_legacy_u32(&eee->supported, + keee->supported); + ethtool_convert_link_mode_to_legacy_u32(&eee->advertised, + keee->advertised); + ethtool_convert_link_mode_to_legacy_u32(&eee->lp_advertised, + keee->lp_advertised); + if (overflow) + pr_warn("Ethtool ioctl interface doesn't support passing EEE linkmodes beyond bit 32\n"); + } else { + eee->supported = keee->supported_u32; + eee->advertised = keee->advertised_u32; + eee->lp_advertised = keee->lp_advertised_u32; + } } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) -- cgit v1.2.3 From 2a71528427c635f0a8bff704b2e62ce81c641d6f Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Sun, 28 Jan 2024 10:30:57 +0100 Subject: wifi: brcmfmac: fix copyright year mentioned in platform_data header The driver found its inception a little after the year 201. According git blame output it was added in 2016 so lets go with that. Fixes: 4d7928959832 ("brcmfmac: switch to new platform data") Reported-by: Dmitry Antipov Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://msgid.link/20240128093057.164791-3-arend.vanspriel@broadcom.com --- include/linux/platform_data/brcmfmac.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h index f922a192fe58..ec99b7b73d1d 100644 --- a/include/linux/platform_data/brcmfmac.h +++ b/include/linux/platform_data/brcmfmac.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 201 Broadcom Corporation + * Copyright (c) 2016 Broadcom Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above -- cgit v1.2.3 From 79b47344bbc5a693a92ed6b2b09dac59254bfac8 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Sun, 28 Jan 2024 18:24:06 -0700 Subject: bpf: btf: Support flags for BTF_SET8 sets This commit adds support for flags on BTF_SET8s. struct btf_id_set8 already supported 32 bits worth of flags, but was only used for alignment purposes before. We now use these bits to encode flags. The first use case is tagging kfunc sets with a flag so that pahole can recognize which BTF_ID_FLAGS(func, ..) are actual kfuncs. Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/7bb152ec76d6c2c930daec88e995bf18484a5ebb.1706491398.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index a9cb10b0e2e9..dca09b7f21dc 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -21,6 +21,7 @@ struct btf_id_set8 { #include /* for __PASTE */ #include /* for __maybe_unused */ +#include /* * Following macros help to define lists of BTF IDs placed @@ -183,17 +184,18 @@ extern struct btf_id_set name; * .word (1 << 3) | (1 << 1) | (1 << 2) * */ -#define __BTF_SET8_START(name, scope) \ +#define __BTF_SET8_START(name, scope, flags) \ +__BTF_ID_LIST(name, local) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " __BTF_ID__set8__" #name "; \n" \ "__BTF_ID__set8__" #name ":; \n" \ -".zero 8 \n" \ +".zero 4 \n" \ +".long " __stringify(flags) "\n" \ ".popsection; \n"); #define BTF_SET8_START(name) \ -__BTF_ID_LIST(name, local) \ -__BTF_SET8_START(name, local) +__BTF_SET8_START(name, local, 0) #define BTF_SET8_END(name) \ asm( \ -- cgit v1.2.3 From a05e90427ef6706f59188b379ad6366b9d298bc5 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Sun, 28 Jan 2024 18:24:07 -0700 Subject: bpf: btf: Add BTF_KFUNCS_START/END macro pair This macro pair is functionally equivalent to BTF_SET8_START/END, except with BTF_SET8_KFUNCS flag set in the btf_id_set8 flags field. The next commit will codemod all kfunc set8s to this new variant such that all kfuncs are tagged as such in .BTF_ids section. Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/d536c57c7c2af428686853cc7396b7a44faa53b7.1706491398.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index dca09b7f21dc..e24aabfe8ecc 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -8,6 +8,9 @@ struct btf_id_set { u32 ids[]; }; +/* This flag implies BTF_SET8 holds kfunc(s) */ +#define BTF_SET8_KFUNCS (1 << 0) + struct btf_id_set8 { u32 cnt; u32 flags; @@ -204,6 +207,12 @@ asm( \ ".popsection; \n"); \ extern struct btf_id_set8 name; +#define BTF_KFUNCS_START(name) \ +__BTF_SET8_START(name, local, BTF_SET8_KFUNCS) + +#define BTF_KFUNCS_END(name) \ +BTF_SET8_END(name) + #else #define BTF_ID_LIST(name) static u32 __maybe_unused name[64]; @@ -218,6 +227,8 @@ extern struct btf_id_set8 name; #define BTF_SET_END(name) #define BTF_SET8_START(name) static struct btf_id_set8 __maybe_unused name = { 0 }; #define BTF_SET8_END(name) +#define BTF_KFUNCS_START(name) static struct btf_id_set8 __maybe_unused name = { .flags = BTF_SET8_KFUNCS }; +#define BTF_KFUNCS_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From 3723b56d6f73f7c8c3b521a80556f129830f6fb9 Mon Sep 17 00:00:00 2001 From: Philippe Schenker Date: Tue, 30 Jan 2024 09:34:19 +0100 Subject: net: dsa: Add KSZ8567 switch support This commit introduces support for the KSZ8567, a robust 7-port Ethernet switch. The KSZ8567 features two RGMII/MII/RMII interfaces, each capable of gigabit speeds, complemented by five 10/100 Mbps MAC/PHYs. Signed-off-by: Philippe Schenker Acked-by: Arun Ramadoss Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20240130083419.135763-2-dev@pschenker.ch Signed-off-by: Paolo Abeni --- drivers/net/dsa/microchip/ksz9477_i2c.c | 4 +++ drivers/net/dsa/microchip/ksz_common.c | 43 ++++++++++++++++++++++++++++- drivers/net/dsa/microchip/ksz_common.h | 1 + drivers/net/dsa/microchip/ksz_spi.c | 5 ++++ include/linux/platform_data/microchip-ksz.h | 1 + 5 files changed, 53 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index cac4a607e54a..82bebee4615c 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -103,6 +103,10 @@ static const struct of_device_id ksz9477_dt_ids[] = { .compatible = "microchip,ksz8563", .data = &ksz_switch_chips[KSZ8563] }, + { + .compatible = "microchip,ksz8567", + .data = &ksz_switch_chips[KSZ8567] + }, { .compatible = "microchip,ksz9567", .data = &ksz_switch_chips[KSZ9567] diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a7b5ddb8656e..9ff5132f3ac6 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1476,6 +1476,39 @@ const struct ksz_chip_data ksz_switch_chips[] = { .gbit_capable = {true, true, true}, }, + [KSZ8567] = { + .chip_id = KSZ8567_CHIP_ID, + .dev_name = "KSZ8567", + .num_vlans = 4096, + .num_alus = 4096, + .num_statics = 16, + .cpu_ports = 0x7F, /* can be configured as cpu port */ + .port_cnt = 7, /* total port count */ + .port_nirqs = 3, + .num_tx_queues = 4, + .tc_cbs_supported = true, + .tc_ets_supported = true, + .ops = &ksz9477_dev_ops, + .mib_names = ksz9477_mib_names, + .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz9477_regs, + .masks = ksz9477_masks, + .shifts = ksz9477_shifts, + .xmii_ctrl0 = ksz9477_xmii_ctrl0, + .xmii_ctrl1 = ksz9477_xmii_ctrl1, + .supports_mii = {false, false, false, false, + false, true, true}, + .supports_rmii = {false, false, false, false, + false, true, true}, + .supports_rgmii = {false, false, false, false, + false, true, true}, + .internal_phy = {true, true, true, true, + true, false, false}, + .gbit_capable = {false, false, false, false, false, + true, true}, + }, + [KSZ9567] = { .chip_id = KSZ9567_CHIP_ID, .dev_name = "KSZ9567", @@ -2649,6 +2682,7 @@ static void ksz_port_teardown(struct dsa_switch *ds, int port) switch (dev->chip_id) { case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: @@ -2705,7 +2739,8 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, dev->chip_id == KSZ9563_CHIP_ID) proto = DSA_TAG_PROTO_KSZ9893; - if (dev->chip_id == KSZ9477_CHIP_ID || + if (dev->chip_id == KSZ8567_CHIP_ID || + dev->chip_id == KSZ9477_CHIP_ID || dev->chip_id == KSZ9896_CHIP_ID || dev->chip_id == KSZ9897_CHIP_ID || dev->chip_id == KSZ9567_CHIP_ID) @@ -2813,6 +2848,7 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) case KSZ8830_CHIP_ID: return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: @@ -2839,6 +2875,7 @@ static int ksz_validate_eee(struct dsa_switch *ds, int port) switch (dev->chip_id) { case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: @@ -3183,6 +3220,7 @@ static int ksz_switch_detect(struct ksz_device *dev) case KSZ9896_CHIP_ID: case KSZ9897_CHIP_ID: case KSZ9567_CHIP_ID: + case KSZ8567_CHIP_ID: case LAN9370_CHIP_ID: case LAN9371_CHIP_ID: case LAN9372_CHIP_ID: @@ -3220,6 +3258,7 @@ static int ksz_cls_flower_add(struct dsa_switch *ds, int port, switch (dev->chip_id) { case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: @@ -3239,6 +3278,7 @@ static int ksz_cls_flower_del(struct dsa_switch *ds, int port, switch (dev->chip_id) { case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: @@ -4142,6 +4182,7 @@ static int ksz_parse_drive_strength(struct ksz_device *dev) case KSZ8794_CHIP_ID: case KSZ8765_CHIP_ID: case KSZ8563_CHIP_ID: + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: case KSZ9563_CHIP_ID: case KSZ9567_CHIP_ID: diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 15612101a155..060c5de9aa05 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -187,6 +187,7 @@ struct ksz_device { /* List of supported models */ enum ksz_model { KSZ8563, + KSZ8567, KSZ8795, KSZ8794, KSZ8765, diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 6f6d878e742c..c8166fb440ab 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -164,6 +164,10 @@ static const struct of_device_id ksz_dt_ids[] = { .compatible = "microchip,ksz8563", .data = &ksz_switch_chips[KSZ8563] }, + { + .compatible = "microchip,ksz8567", + .data = &ksz_switch_chips[KSZ8567] + }, { .compatible = "microchip,ksz9567", .data = &ksz_switch_chips[KSZ9567] @@ -204,6 +208,7 @@ static const struct spi_device_id ksz_spi_ids[] = { { "ksz9893" }, { "ksz9563" }, { "ksz8563" }, + { "ksz8567" }, { "ksz9567" }, { "lan9370" }, { "lan9371" }, diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index f177416635a2..8c659db4da6b 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -33,6 +33,7 @@ enum ksz_chip_id { KSZ9897_CHIP_ID = 0x00989700, KSZ9893_CHIP_ID = 0x00989300, KSZ9563_CHIP_ID = 0x00956300, + KSZ8567_CHIP_ID = 0x00856700, KSZ9567_CHIP_ID = 0x00956700, LAN9370_CHIP_ID = 0x00937000, LAN9371_CHIP_ID = 0x00937100, -- cgit v1.2.3 From c1f5204efcbcced83f67f12fa8f1a7f5f244fb87 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 28 Jan 2024 22:21:04 -0800 Subject: cpumask: add cpumask_weight_andnot() Similarly to cpumask_weight_and(), cpumask_weight_andnot() is a handy helper that may help to avoid creating an intermediate mask just to calculate number of bits that set in a 1st given mask, and clear in 2nd one. Signed-off-by: Yury Norov Reviewed-by: Jacob Keller Signed-off-by: Paolo Abeni --- include/linux/bitmap.h | 12 ++++++++++++ include/linux/cpumask.h | 13 +++++++++++++ lib/bitmap.c | 7 +++++++ 3 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 99451431e4d6..5814e9ee40ba 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -54,6 +54,7 @@ struct device; * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap + * bitmap_weight_andnot(src1, src2, nbits) Hamming Weight of andnot'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area @@ -169,6 +170,8 @@ bool __bitmap_subset(const unsigned long *bitmap1, unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -425,6 +428,15 @@ unsigned long bitmap_weight_and(const unsigned long *src1, return __bitmap_weight_and(src1, src2, nbits); } +static __always_inline +unsigned long bitmap_weight_andnot(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_andnot(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index cfb545841a2c..228c23eb36d2 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -719,6 +719,19 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } +/** + * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + * + * Return: count of bits set in both *srcp1 and *srcp2 + */ +static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); +} + /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result diff --git a/lib/bitmap.c b/lib/bitmap.c index 09522af227f1..b97692854966 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -348,6 +348,13 @@ unsigned int __bitmap_weight_and(const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_weight_and); +unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); +} +EXPORT_SYMBOL(__bitmap_weight_andnot); + void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); -- cgit v1.2.3 From dcee228078c34b63089c4b589d4bddf08019d0f6 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 28 Jan 2024 22:21:05 -0800 Subject: cpumask: define cleanup function for cpumasks Now we can simplify code that allocates cpumasks for local needs. Signed-off-by: Yury Norov Signed-off-by: Paolo Abeni --- include/linux/cpumask.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 228c23eb36d2..1c29947db848 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -7,6 +7,7 @@ * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ +#include #include #include #include @@ -990,6 +991,8 @@ static inline bool cpumask_available(cpumask_var_t mask) } #endif /* CONFIG_CPUMASK_OFFSTACK */ +DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); + /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); -- cgit v1.2.3 From e2ca9e75849e63eab6544549b6888595997e8153 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 30 Jan 2024 13:08:30 +0100 Subject: dpll: extend lock_status_get() op by status error and expose to user Pass additional argunent status_error over lock_status_get() so drivers can fill it up. In case they do, expose the value over previously introduced attribute to user. Do it only in case the current lock_status is either "unlocked" or "holdover". Signed-off-by: Jiri Pirko Acked-by: Vadim Fedorenko Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- drivers/dpll/dpll_netlink.c | 9 ++++++++- drivers/net/ethernet/intel/ice/ice_dpll.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/dpll.c | 9 +++++---- drivers/ptp/ptp_ocp.c | 9 +++++---- include/linux/dpll.h | 1 + 5 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 314bb3775465..cf3313517ae1 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -121,14 +121,21 @@ dpll_msg_add_lock_status(struct sk_buff *msg, struct dpll_device *dpll, struct netlink_ext_ack *extack) { const struct dpll_device_ops *ops = dpll_device_ops(dpll); + enum dpll_lock_status_error status_error = 0; enum dpll_lock_status status; int ret; - ret = ops->lock_status_get(dpll, dpll_priv(dpll), &status, extack); + ret = ops->lock_status_get(dpll, dpll_priv(dpll), &status, + &status_error, extack); if (ret) return ret; if (nla_put_u32(msg, DPLL_A_LOCK_STATUS, status)) return -EMSGSIZE; + if (status_error && + (status == DPLL_LOCK_STATUS_UNLOCKED || + status == DPLL_LOCK_STATUS_HOLDOVER) && + nla_put_u32(msg, DPLL_A_LOCK_STATUS_ERROR, status_error)) + return -EMSGSIZE; return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index b9c5eced6326..c0256564e998 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -488,6 +488,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, * @dpll: registered dpll pointer * @dpll_priv: private data pointer passed on dpll registration * @status: on success holds dpll's lock status + * @status_error: status error value * @extack: error reporting * * Dpll subsystem callback, provides dpll's lock status. @@ -500,6 +501,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, static int ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv, enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, struct netlink_ext_ack *extack) { struct ice_dpll *d = dpll_priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 18fed2b34fb1..07f43d5c90c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -118,10 +118,11 @@ mlx5_dpll_pin_ffo_get(struct mlx5_dpll_synce_status *synce_status, return 0; } -static int mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll, - void *priv, - enum dpll_lock_status *status, - struct netlink_ext_ack *extack) +static int +mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll, void *priv, + enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, + struct netlink_ext_ack *extack) { struct mlx5_dpll_synce_status synce_status; struct mlx5_dpll *mdpll = priv; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 5f858e426bbd..9507681e0d12 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4209,10 +4209,11 @@ ptp_ocp_detach(struct ptp_ocp *bp) device_unregister(&bp->dev); } -static int ptp_ocp_dpll_lock_status_get(const struct dpll_device *dpll, - void *priv, - enum dpll_lock_status *status, - struct netlink_ext_ack *extack) +static int +ptp_ocp_dpll_lock_status_get(const struct dpll_device *dpll, void *priv, + enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, + struct netlink_ext_ack *extack) { struct ptp_ocp *bp = priv; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 9cf896ea1d41..9cb02ad73d51 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -19,6 +19,7 @@ struct dpll_device_ops { enum dpll_mode *mode, struct netlink_ext_ack *extack); int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv, enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, struct netlink_ext_ack *extack); int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv, s32 *temp, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 2c54a4d71246379f4ffb9beb6a780f9a49fdfc24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 30 Jan 2024 13:08:31 +0100 Subject: net/mlx5: DPLL, Implement lock status error value Fill-up the lock status error value properly. Signed-off-by: Jiri Pirko Acked-by: Vadim Fedorenko Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mellanox/mlx5/core/dpll.c | 23 +++++++++++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 8 ++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 07f43d5c90c6..4ad3d2d3d4c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -41,6 +41,7 @@ struct mlx5_dpll_synce_status { enum mlx5_msees_oper_status oper_status; bool ho_acq; bool oper_freq_measure; + enum mlx5_msees_failure_reason failure_reason; s32 frequency_diff; }; @@ -60,6 +61,7 @@ mlx5_dpll_synce_status_get(struct mlx5_core_dev *mdev, synce_status->oper_status = MLX5_GET(msees_reg, out, oper_status); synce_status->ho_acq = MLX5_GET(msees_reg, out, ho_acq); synce_status->oper_freq_measure = MLX5_GET(msees_reg, out, oper_freq_measure); + synce_status->failure_reason = MLX5_GET(msees_reg, out, failure_reason); synce_status->frequency_diff = MLX5_GET(msees_reg, out, frequency_diff); return 0; } @@ -99,6 +101,26 @@ mlx5_dpll_lock_status_get(struct mlx5_dpll_synce_status *synce_status) } } +static enum dpll_lock_status_error +mlx5_dpll_lock_status_error_get(struct mlx5_dpll_synce_status *synce_status) +{ + switch (synce_status->oper_status) { + case MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER: + fallthrough; + case MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING: + switch (synce_status->failure_reason) { + case MLX5_MSEES_FAILURE_REASON_PORT_DOWN: + return DPLL_LOCK_STATUS_ERROR_MEDIA_DOWN; + case MLX5_MSEES_FAILURE_REASON_TOO_HIGH_FREQUENCY_DIFF: + return DPLL_LOCK_STATUS_ERROR_FRACTIONAL_FREQUENCY_OFFSET_TOO_HIGH; + default: + return DPLL_LOCK_STATUS_ERROR_UNDEFINED; + } + default: + return DPLL_LOCK_STATUS_ERROR_NONE; + } +} + static enum dpll_pin_state mlx5_dpll_pin_state_get(struct mlx5_dpll_synce_status *synce_status) { @@ -132,6 +154,7 @@ mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll, void *priv, if (err) return err; *status = mlx5_dpll_lock_status_get(&synce_status); + *status_error = mlx5_dpll_lock_status_error_get(&synce_status); return 0; } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c726f90ab752..6c44f107b8ba 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -12705,6 +12705,14 @@ enum mlx5_msees_oper_status { MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING = 0x5, }; +enum mlx5_msees_failure_reason { + MLX5_MSEES_FAILURE_REASON_UNDEFINED_ERROR = 0x0, + MLX5_MSEES_FAILURE_REASON_PORT_DOWN = 0x1, + MLX5_MSEES_FAILURE_REASON_TOO_HIGH_FREQUENCY_DIFF = 0x2, + MLX5_MSEES_FAILURE_REASON_NET_SYNCHRONIZER_DEVICE_ERROR = 0x3, + MLX5_MSEES_FAILURE_REASON_LACK_OF_RESOURCES = 0x4, +}; + struct mlx5_ifc_msees_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; -- cgit v1.2.3 From c1e6148cb4f83cec841db1f066e8db4a86c1f118 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Sat, 27 Jan 2024 19:52:34 +0200 Subject: bpf: Preserve boundaries and track scalars on narrowing fill When the width of a fill is smaller than the width of the preceding spill, the information about scalar boundaries can still be preserved, as long as it's coerced to the right width (done by coerce_reg_to_size). Even further, if the actual value fits into the fill width, the ID can be preserved as well for further tracking of equal scalars. Implement the above improvements, which makes narrowing fills behave the same as narrowing spills and MOVs between registers. Two tests are adjusted to accommodate for endianness differences and to take into account that it's now allowed to do a narrowing fill from the least significant bits. reg_bounds_sync is added to coerce_reg_to_size to correctly adjust umin/umax boundaries after the var_off truncation, for example, a 64-bit value 0xXXXXXXXX00000000, when read as a 32-bit, gets umin = 0, umax = 0xFFFFFFFF, var_off = (0x0; 0xffffffff00000000), which needs to be synced down to umax = 0, otherwise reg_bounds_sanity_check doesn't pass. Signed-off-by: Maxim Mikityanskiy Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240127175237.526726-4-maxtram95@gmail.com --- include/linux/bpf_verifier.h | 9 ++++++++ kernel/bpf/verifier.c | 15 +++++++++---- .../selftests/bpf/progs/verifier_spill_fill.c | 26 ++++++++++++++++------ 3 files changed, 39 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0dcde339dc7e..84365e6dd85d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -919,6 +919,15 @@ static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env) env->scratched_stack_slots = ~0ULL; } +static inline bool bpf_stack_narrow_access_ok(int off, int fill_size, int spill_size) +{ +#ifdef __BIG_ENDIAN + off -= spill_size - fill_size; +#endif + + return !(off % BPF_REG_SIZE); +} + const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type); const char *dynptr_type_str(enum bpf_dynptr_type type); const char *iter_type_str(const struct btf *btf, u32 btf_id); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 28f62f24da7e..82af971926ac 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4778,7 +4778,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - if (!(off % BPF_REG_SIZE) && size == spill_size) { + if (size <= spill_size && + bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -4786,6 +4787,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; + + /* Break the relation on a narrowing fill. + * coerce_reg_to_size will adjust the boundaries. + */ + if (get_reg_width(reg) > size * BITS_PER_BYTE) + state->regs[dst_regno].id = 0; } else { int spill_cnt = 0, zero_cnt = 0; @@ -6061,10 +6068,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ - if (size < 4) { + if (size < 4) __mark_reg32_unbounded(reg); - reg_bounds_sync(reg); - } + + reg_bounds_sync(reg); } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index f9803005e1c0..3e5d063ea7e8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -217,7 +217,7 @@ __naked void uninit_u32_from_the_stack(void) SEC("tc") __description("Spill a u32 const scalar. Refill as u16. Offset to skb->data") -__failure __msg("invalid access to packet") +__success __retval(0) __naked void u16_offset_to_skb_data(void) { asm volatile (" \ @@ -225,13 +225,19 @@ __naked void u16_offset_to_skb_data(void) r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ w4 = 20; \ *(u32*)(r10 - 8) = r4; \ - r4 = *(u16*)(r10 - 8); \ + " +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r4 = *(u16*)(r10 - 8);" +#else + "r4 = *(u16*)(r10 - 6);" +#endif + " \ r0 = r2; \ - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */\ r0 += r4; \ - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\ + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\ if r0 > r3 goto l0_%=; \ - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\ + /* r0 = *(u32 *)r2 R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\ r0 = *(u32*)(r2 + 0); \ l0_%=: r0 = 0; \ exit; \ @@ -268,7 +274,7 @@ l0_%=: r0 = 0; \ } SEC("tc") -__description("Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data") +__description("Spill a u32 const scalar. Refill as u16 from MSB. Offset to skb->data") __failure __msg("invalid access to packet") __naked void _6_offset_to_skb_data(void) { @@ -277,7 +283,13 @@ __naked void _6_offset_to_skb_data(void) r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ w4 = 20; \ *(u32*)(r10 - 8) = r4; \ - r4 = *(u16*)(r10 - 6); \ + " +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r4 = *(u16*)(r10 - 6);" +#else + "r4 = *(u16*)(r10 - 8);" +#endif + " \ r0 = r2; \ /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ r0 += r4; \ -- cgit v1.2.3 From bd8a8d5ec5048ef74002d9f3db5cae971e68712c Mon Sep 17 00:00:00 2001 From: Yunjian Wang Date: Fri, 2 Feb 2024 15:25:55 +0800 Subject: tun: Fix code style issues in This fixes the following code style problem: - WARNING: please, no spaces at the start of a line - CHECK: Please use a blank line after function/struct/union/enum declarations Signed-off-by: Yunjian Wang Reviewed-by: Jiri Pirko Reviewed-by: Willem de Bruijn Acked-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/if_tun.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 2a7660843444..043d442994b0 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -27,44 +27,54 @@ struct tun_xdp_hdr { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); + static inline bool tun_is_xdp_frame(void *ptr) { - return (unsigned long)ptr & TUN_XDP_FLAG; + return (unsigned long)ptr & TUN_XDP_FLAG; } + static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) { - return (void *)((unsigned long)xdp | TUN_XDP_FLAG); + return (void *)((unsigned long)xdp | TUN_XDP_FLAG); } + static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) { - return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); + return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); } + void tun_ptr_free(void *ptr); #else #include #include struct file; struct socket; + static inline struct socket *tun_get_socket(struct file *f) { return ERR_PTR(-EINVAL); } + static inline struct ptr_ring *tun_get_tx_ring(struct file *f) { return ERR_PTR(-EINVAL); } + static inline bool tun_is_xdp_frame(void *ptr) { return false; } + static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) { return NULL; } + static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) { return NULL; } + static inline void tun_ptr_free(void *ptr) { } -- cgit v1.2.3 From ffabe98cb576097b77d404d39e8b3df03caa986a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Feb 2024 10:11:06 +0000 Subject: net: make dev_unreg_count global We can use a global dev_unreg_count counter instead of a per netns one. As a bonus we can factorize the changes done on it for bulk device removals. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 1 + include/net/net_namespace.h | 2 -- net/core/dev.c | 12 +++++++++--- net/core/rtnetlink.c | 11 +---------- 4 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 410529fca18b..21780608cf47 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -47,6 +47,7 @@ extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; +extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; extern struct rw_semaphore net_rwsem; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 13b3a4e29fdb..cd0c2eedbb5e 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -67,8 +67,6 @@ struct net { */ spinlock_t rules_mod_lock; - atomic_t dev_unreg_count; - unsigned int dev_base_seq; /* protected by rtnl_mutex */ u32 ifindex; diff --git a/net/core/dev.c b/net/core/dev.c index b53b9c94de40..27ba057d06c4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9698,11 +9698,11 @@ static void dev_index_release(struct net *net, int ifindex) /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); - atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -10529,6 +10529,7 @@ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; + int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; @@ -10565,6 +10566,7 @@ void netdev_run_todo(void) linkwatch_sync_dev(dev); } + cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); @@ -10582,12 +10584,13 @@ void netdev_run_todo(void) if (dev->needs_free_netdev) free_netdev(dev); - if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) - wake_up(&netdev_unregistering_wq); + cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } + if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) + wake_up(&netdev_unregistering_wq); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has @@ -11034,6 +11037,7 @@ void unregister_netdevice_many_notify(struct list_head *head, { struct net_device *dev, *tmp; LIST_HEAD(close_head); + int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -11130,7 +11134,9 @@ void unregister_netdevice_many_notify(struct list_head *head, list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); + cnt++; } + atomic_add(cnt, &dev_unreg_count); list_del(head); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f6f29eb03ec2..31f433950c8d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -483,24 +483,15 @@ EXPORT_SYMBOL_GPL(__rtnl_link_unregister); */ static void rtnl_lock_unregistering_all(void) { - struct net *net; - bool unregistering; DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { - unregistering = false; rtnl_lock(); /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ - for_each_net(net) { - if (atomic_read(&net->dev_unreg_count) > 0) { - unregistering = true; - break; - } - } - if (!unregistering) + if (!atomic_read(&dev_unreg_count)) break; __rtnl_unlock(); -- cgit v1.2.3 From 2719a9e7156c4b3983b43db467c1ff96801bda99 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 31 Jan 2024 23:37:25 +0100 Subject: wifi: cw1200: Convert to GPIO descriptors The CW1200 uses two GPIOs to control the powerup and reset pins, get these from GPIO descriptors instead of being passed as platform data from boardfiles. The RESET line will need to be marked as active low as we will let gpiolib handle the polarity inversion. The SDIO case is a bit special since the "card" need to be powered up before it gets detected on the SDIO bus and properly probed. Fix this by using board-specific GPIOs assigned to device "NULL". There are currently no in-tree users. Signed-off-by: Linus Walleij Signed-off-by: Kalle Valo Link: https://msgid.link/20240131-descriptors-wireless-v1-6-e1c7c5d68746@linaro.org --- drivers/net/wireless/st/cw1200/cw1200_sdio.c | 42 +++++++++------- drivers/net/wireless/st/cw1200/cw1200_spi.c | 71 ++++++++++++++++------------ include/linux/platform_data/net-cw1200.h | 4 -- 3 files changed, 65 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c index 4c30b5772ce0..00c4731d8f8e 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c +++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include #include @@ -178,12 +178,15 @@ static int cw1200_sdio_irq_unsubscribe(struct hwbus_priv *self) return ret; } +/* Like the rest of the driver, this only supports one device per system */ +static struct gpio_desc *cw1200_reset; +static struct gpio_desc *cw1200_powerup; + static int cw1200_sdio_off(const struct cw1200_platform_data_sdio *pdata) { - if (pdata->reset) { - gpio_set_value(pdata->reset, 0); + if (cw1200_reset) { + gpiod_set_value(cw1200_reset, 0); msleep(30); /* Min is 2 * CLK32K cycles */ - gpio_free(pdata->reset); } if (pdata->power_ctrl) @@ -196,16 +199,21 @@ static int cw1200_sdio_off(const struct cw1200_platform_data_sdio *pdata) static int cw1200_sdio_on(const struct cw1200_platform_data_sdio *pdata) { - /* Ensure I/Os are pulled low */ - if (pdata->reset) { - gpio_request(pdata->reset, "cw1200_wlan_reset"); - gpio_direction_output(pdata->reset, 0); + /* Ensure I/Os are pulled low (reset is active low) */ + cw1200_reset = devm_gpiod_get_optional(NULL, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(cw1200_reset)) { + pr_err("could not get CW1200 SDIO reset GPIO\n"); + return PTR_ERR(cw1200_reset); } - if (pdata->powerup) { - gpio_request(pdata->powerup, "cw1200_wlan_powerup"); - gpio_direction_output(pdata->powerup, 0); + gpiod_set_consumer_name(cw1200_reset, "cw1200_wlan_reset"); + cw1200_powerup = devm_gpiod_get_optional(NULL, "powerup", GPIOD_OUT_LOW); + if (IS_ERR(cw1200_powerup)) { + pr_err("could not get CW1200 SDIO powerup GPIO\n"); + return PTR_ERR(cw1200_powerup); } - if (pdata->reset || pdata->powerup) + gpiod_set_consumer_name(cw1200_powerup, "cw1200_wlan_powerup"); + + if (cw1200_reset || cw1200_powerup) msleep(10); /* Settle time? */ /* Enable 3v3 and 1v8 to hardware */ @@ -226,13 +234,13 @@ static int cw1200_sdio_on(const struct cw1200_platform_data_sdio *pdata) } /* Enable POWERUP signal */ - if (pdata->powerup) { - gpio_set_value(pdata->powerup, 1); + if (cw1200_powerup) { + gpiod_set_value(cw1200_powerup, 1); msleep(250); /* or more..? */ } - /* Enable RSTn signal */ - if (pdata->reset) { - gpio_set_value(pdata->reset, 1); + /* Deassert RSTn signal, note active low */ + if (cw1200_reset) { + gpiod_set_value(cw1200_reset, 0); msleep(50); /* Or more..? */ } return 0; diff --git a/drivers/net/wireless/st/cw1200/cw1200_spi.c b/drivers/net/wireless/st/cw1200/cw1200_spi.c index b27b57fc25bc..fb3aafcafe18 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/st/cw1200/cw1200_spi.c @@ -11,7 +11,7 @@ */ #include -#include +#include #include #include #include @@ -38,6 +38,8 @@ struct hwbus_priv { const struct cw1200_platform_data_spi *pdata; spinlock_t lock; /* Serialize all bus operations */ wait_queue_head_t wq; + struct gpio_desc *reset; + struct gpio_desc *powerup; int claimed; }; @@ -269,12 +271,12 @@ static void cw1200_spi_irq_unsubscribe(struct hwbus_priv *self) free_irq(self->func->irq, self); } -static int cw1200_spi_off(const struct cw1200_platform_data_spi *pdata) +static int cw1200_spi_off(struct hwbus_priv *self, const struct cw1200_platform_data_spi *pdata) { - if (pdata->reset) { - gpio_set_value(pdata->reset, 0); + if (self->reset) { + /* Assert RESET, note active low */ + gpiod_set_value(self->reset, 1); msleep(30); /* Min is 2 * CLK32K cycles */ - gpio_free(pdata->reset); } if (pdata->power_ctrl) @@ -285,18 +287,12 @@ static int cw1200_spi_off(const struct cw1200_platform_data_spi *pdata) return 0; } -static int cw1200_spi_on(const struct cw1200_platform_data_spi *pdata) +static int cw1200_spi_on(struct hwbus_priv *self, const struct cw1200_platform_data_spi *pdata) { /* Ensure I/Os are pulled low */ - if (pdata->reset) { - gpio_request(pdata->reset, "cw1200_wlan_reset"); - gpio_direction_output(pdata->reset, 0); - } - if (pdata->powerup) { - gpio_request(pdata->powerup, "cw1200_wlan_powerup"); - gpio_direction_output(pdata->powerup, 0); - } - if (pdata->reset || pdata->powerup) + gpiod_direction_output(self->reset, 1); /* Active low */ + gpiod_direction_output(self->powerup, 0); + if (self->reset || self->powerup) msleep(10); /* Settle time? */ /* Enable 3v3 and 1v8 to hardware */ @@ -317,13 +313,13 @@ static int cw1200_spi_on(const struct cw1200_platform_data_spi *pdata) } /* Enable POWERUP signal */ - if (pdata->powerup) { - gpio_set_value(pdata->powerup, 1); + if (self->powerup) { + gpiod_set_value(self->powerup, 1); msleep(250); /* or more..? */ } - /* Enable RSTn signal */ - if (pdata->reset) { - gpio_set_value(pdata->reset, 1); + /* Assert RSTn signal, note active low */ + if (self->reset) { + gpiod_set_value(self->reset, 0); msleep(50); /* Or more..? */ } return 0; @@ -375,20 +371,33 @@ static int cw1200_spi_probe(struct spi_device *func) spi_get_chipselect(func, 0), func->mode, func->bits_per_word, func->max_speed_hz); - if (cw1200_spi_on(plat_data)) { + self = devm_kzalloc(&func->dev, sizeof(*self), GFP_KERNEL); + if (!self) { + pr_err("Can't allocate SPI hwbus_priv."); + return -ENOMEM; + } + + /* Request reset asserted */ + self->reset = devm_gpiod_get_optional(&func->dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(self->reset)) + return dev_err_probe(&func->dev, PTR_ERR(self->reset), + "could not get reset GPIO\n"); + gpiod_set_consumer_name(self->reset, "cw1200_wlan_reset"); + + self->powerup = devm_gpiod_get_optional(&func->dev, "powerup", GPIOD_OUT_LOW); + if (IS_ERR(self->powerup)) + return dev_err_probe(&func->dev, PTR_ERR(self->powerup), + "could not get powerup GPIO\n"); + gpiod_set_consumer_name(self->reset, "cw1200_wlan_powerup"); + + if (cw1200_spi_on(self, plat_data)) { pr_err("spi_on() failed!\n"); - return -1; + return -ENODEV; } if (spi_setup(func)) { pr_err("spi_setup() failed!\n"); - return -1; - } - - self = devm_kzalloc(&func->dev, sizeof(*self), GFP_KERNEL); - if (!self) { - pr_err("Can't allocate SPI hwbus_priv."); - return -ENOMEM; + return -ENODEV; } self->pdata = plat_data; @@ -410,7 +419,7 @@ static int cw1200_spi_probe(struct spi_device *func) if (status) { cw1200_spi_irq_unsubscribe(self); - cw1200_spi_off(plat_data); + cw1200_spi_off(self, plat_data); } return status; @@ -428,7 +437,7 @@ static void cw1200_spi_disconnect(struct spi_device *func) self->core = NULL; } } - cw1200_spi_off(dev_get_platdata(&func->dev)); + cw1200_spi_off(self, dev_get_platdata(&func->dev)); } static int __maybe_unused cw1200_spi_suspend(struct device *dev) diff --git a/include/linux/platform_data/net-cw1200.h b/include/linux/platform_data/net-cw1200.h index c510734405bb..89d0ec6f7d46 100644 --- a/include/linux/platform_data/net-cw1200.h +++ b/include/linux/platform_data/net-cw1200.h @@ -14,8 +14,6 @@ struct cw1200_platform_data_spi { /* All others are optional */ bool have_5ghz; - int reset; /* GPIO to RSTn signal (0 disables) */ - int powerup; /* GPIO to POWERUP signal (0 disables) */ int (*power_ctrl)(const struct cw1200_platform_data_spi *pdata, bool enable); /* Control 3v3 / 1v8 supply */ int (*clk_ctrl)(const struct cw1200_platform_data_spi *pdata, @@ -30,8 +28,6 @@ struct cw1200_platform_data_sdio { /* All others are optional */ bool have_5ghz; bool no_nptb; /* SDIO hardware does not support non-power-of-2-blocksizes */ - int reset; /* GPIO to RSTn signal (0 disables) */ - int powerup; /* GPIO to POWERUP signal (0 disables) */ int irq; /* IRQ line or 0 to use SDIO IRQ */ int (*power_ctrl)(const struct cw1200_platform_data_sdio *pdata, bool enable); /* Control 3v3 / 1v8 supply */ -- cgit v1.2.3 From fd2bc4195d5107f88c1b90e1ec935888ccbfc5c0 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 3 Oct 2023 20:57:20 +0300 Subject: xfrm: generalize xdo_dev_state_update_curlft to allow statistics update In order to allow drivers to fill all statistics, change the name of xdo_dev_state_update_curlft to be xdo_dev_state_update_stats. Acked-by: Steffen Klassert Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- Documentation/networking/xfrm_device.rst | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 7 ++++--- include/linux/netdevice.h | 2 +- include/net/xfrm.h | 11 ++++------- net/xfrm/xfrm_state.c | 4 ++-- net/xfrm/xfrm_user.c | 2 +- 6 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst index 535077cbeb07..bfea9d8579ed 100644 --- a/Documentation/networking/xfrm_device.rst +++ b/Documentation/networking/xfrm_device.rst @@ -71,9 +71,9 @@ Callbacks to implement bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); + void (*xdo_dev_state_update_stats) (struct xfrm_state *x); /* Solely packet offload callbacks */ - void (*xdo_dev_state_update_curlft) (struct xfrm_state *x); int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack); void (*xdo_dev_policy_delete) (struct xfrm_policy *x); void (*xdo_dev_policy_free) (struct xfrm_policy *x); @@ -191,6 +191,6 @@ xdo_dev_policy_free() on any remaining offloaded states. Outcome of HW handling packets, the XFRM core can't count hard, soft limits. The HW/driver are responsible to perform it and provide accurate data when -xdo_dev_state_update_curlft() is called. In case of one of these limits +xdo_dev_state_update_stats() is called. In case of one of these limits occuried, the driver needs to call to xfrm_state_check_expire() to make sure that XFRM performs rekeying sequence. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 05612d9c6080..f160522fbe75 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -984,7 +984,7 @@ static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x) queue_work(sa_entry->ipsec->wq, &work->work); } -static void mlx5e_xfrm_update_curlft(struct xfrm_state *x) +static void mlx5e_xfrm_update_stats(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); struct mlx5e_ipsec_rule *ipsec_rule = &sa_entry->ipsec_rule; @@ -993,7 +993,8 @@ static void mlx5e_xfrm_update_curlft(struct xfrm_state *x) lockdep_assert(lockdep_is_held(&x->lock) || lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex)); - if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) + if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ || + x->xso.type != XFRM_DEV_OFFLOAD_PACKET) return; mlx5_fc_query_cached(ipsec_rule->fc, &bytes, &packets, &lastuse); @@ -1156,7 +1157,7 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, - .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, + .xdo_dev_state_update_stats = mlx5e_xfrm_update_stats, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, .xdo_dev_policy_delete = mlx5e_xfrm_del_policy, .xdo_dev_policy_free = mlx5e_xfrm_free_policy, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 118c40258d07..9538576dbebc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1062,7 +1062,7 @@ struct xfrmdev_ops { bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); - void (*xdo_dev_state_update_curlft) (struct xfrm_state *x); + void (*xdo_dev_state_update_stats) (struct xfrm_state *x); int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack); void (*xdo_dev_policy_delete) (struct xfrm_policy *x); void (*xdo_dev_policy_free) (struct xfrm_policy *x); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1d107241b901..4ca2f3205190 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1578,21 +1578,18 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); #ifdef CONFIG_XFRM_OFFLOAD -static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x) +static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) { struct xfrm_dev_offload *xdo = &x->xso; struct net_device *dev = xdo->dev; - if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) - return; - if (dev && dev->xfrmdev_ops && - dev->xfrmdev_ops->xdo_dev_state_update_curlft) - dev->xfrmdev_ops->xdo_dev_state_update_curlft(x); + dev->xfrmdev_ops->xdo_dev_state_update_stats) + dev->xfrmdev_ops->xdo_dev_state_update_stats(x); } #else -static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x) {} +static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) {} #endif void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index bda5327bf34d..d8701b2d0d57 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -570,7 +570,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) int err = 0; spin_lock(&x->lock); - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); if (x->km.state == XFRM_STATE_DEAD) goto out; @@ -1935,7 +1935,7 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ad01997c3aa9..dc4f9b8d7cb0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -902,7 +902,7 @@ static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) memcpy(&p->sel, &x->sel, sizeof(p->sel)); memcpy(&p->lft, &x->lft, sizeof(p->lft)); if (x->xso.dev) - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); memcpy(&p->curlft, &x->curlft, sizeof(p->curlft)); put_unaligned(x->stats.replay_window, &p->stats.replay_window); put_unaligned(x->stats.replay, &p->stats.replay); -- cgit v1.2.3 From 91a72ada66053b4dba95cf1a60a5a23fdbd6faf7 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 26 Dec 2023 10:22:08 +0200 Subject: net/mlx5: Remove initial segmentation duplicate definitions Device definitions belong in mlx5_ifc, remove the duplicates in mlx5_core.h. Signed-off-by: Gal Pressman Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/health.c | 20 ++++++++++---------- drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 7 ------- include/linux/mlx5/mlx5_ifc.h | 1 + 4 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 58f4c0d0fafa..e7faf7e73ca4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -366,18 +366,18 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) return -EIO; } - mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED); + mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED); /* Loop until device state turns to disable */ end = jiffies + msecs_to_jiffies(delay_ms); do { - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) break; cond_resched(); } while (!time_after(jiffies, end)); - if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) { dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", mlx5_get_nic_state(dev), delay_ms); return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 5c2ac2d9dbd9..9463ede84d8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -116,9 +116,9 @@ u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev) return MLX5_SENSOR_PCI_COMM_ERR; if (pci_channel_offline(dev->pdev)) return MLX5_SENSOR_PCI_ERR; - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) return MLX5_SENSOR_NIC_DISABLED; - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_SW_RESET) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET) return MLX5_SENSOR_NIC_SW_RESET; if (sensor_fw_synd_rfr(dev)) return MLX5_SENSOR_FW_SYND_RFR; @@ -185,7 +185,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev) /* Write the NIC interface field to initiate the reset, the command * interface address also resides here, don't overwrite it. */ - mlx5_set_nic_state(dev, MLX5_NIC_IFC_SW_RESET); + mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET); return true; } @@ -246,13 +246,13 @@ recover_from_sw_reset: /* Recover from SW reset */ end = jiffies + msecs_to_jiffies(delay_ms); do { - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) break; msleep(20); } while (!time_after(jiffies, end)); - if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) { dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", mlx5_get_nic_state(dev), delay_ms); } @@ -272,26 +272,26 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) u8 nic_interface = mlx5_get_nic_state(dev); switch (nic_interface) { - case MLX5_NIC_IFC_FULL: + case MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER: mlx5_core_warn(dev, "Expected to see disabled NIC but it is full driver\n"); break; - case MLX5_NIC_IFC_DISABLED: + case MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED: mlx5_core_warn(dev, "starting teardown\n"); break; - case MLX5_NIC_IFC_NO_DRAM_NIC: + case MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC: mlx5_core_warn(dev, "Expected to see disabled NIC but it is no dram nic\n"); break; - case MLX5_NIC_IFC_SW_RESET: + case MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET: /* The IFC mode field is 3 bits, so it will read 0x7 in 2 cases: * 1. PCI has been disabled (ie. PCI-AER, PF driver unloaded * and this is a VF), this is not recoverable by SW reset. * Logging of this is handled elsewhere. * 2. FW reset has been issued by another function, driver can * be reloaded to recover after the mode switches to - * MLX5_NIC_IFC_DISABLED. + * MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED. */ if (dev->priv.health.fatal_error != MLX5_SENSOR_PCI_COMM_ERR) mlx5_core_warn(dev, "NIC SW reset in progress\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index a79b7959361b..58732f44940f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -312,13 +312,6 @@ static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) return ret; } -enum { - MLX5_NIC_IFC_FULL = 0, - MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2, - MLX5_NIC_IFC_SW_RESET = 7 -}; - u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6c44f107b8ba..7f5e846eb46d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10661,6 +10661,7 @@ enum { MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC = 0x2, + MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET = 0x7, }; enum { -- cgit v1.2.3 From 0bd199fd9c19aa545f677fd0a99f2be101cb6309 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 2 Feb 2024 17:41:45 +0000 Subject: net: phy: constify phydev->drv Device driver structures are shared between all devices that they match, and thus nothing should never write to the device driver structure through the phydev->drv pointer. Let's make this pointer const to catch code that attempts to do so. Suggested-by: Christian Marangi Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1rVxXt-002YqY-9G@rmk-PC.armlinux.org.uk Signed-off-by: Paolo Abeni --- drivers/net/phy/phy.c | 3 +-- drivers/net/phy/phy_device.c | 6 +++--- drivers/net/phy/xilinx_gmii2rgmii.c | 2 +- include/linux/phy.h | 2 +- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 3b9531143be1..14224e06d69f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1290,7 +1290,6 @@ int phy_disable_interrupts(struct phy_device *phydev) static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; - struct phy_driver *drv = phydev->drv; irqreturn_t ret; /* Wakeup interrupts may occur during a system sleep transition. @@ -1316,7 +1315,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) } mutex_lock(&phydev->lock); - ret = drv->handle_interrupt(phydev); + ret = phydev->drv->handle_interrupt(phydev); mutex_unlock(&phydev->lock); return ret; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 52828d1c64f7..2eed8f03621d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1413,7 +1413,7 @@ int phy_sfp_probe(struct phy_device *phydev, } EXPORT_SYMBOL(phy_sfp_probe); -static bool phy_drv_supports_irq(struct phy_driver *phydrv) +static bool phy_drv_supports_irq(const struct phy_driver *phydrv) { return phydrv->config_intr && phydrv->handle_interrupt; } @@ -1867,7 +1867,7 @@ int phy_suspend(struct phy_device *phydev) { struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct net_device *netdev = phydev->attached_dev; - struct phy_driver *phydrv = phydev->drv; + const struct phy_driver *phydrv = phydev->drv; int ret; if (phydev->suspended) @@ -1892,7 +1892,7 @@ EXPORT_SYMBOL(phy_suspend); int __phy_resume(struct phy_device *phydev) { - struct phy_driver *phydrv = phydev->drv; + const struct phy_driver *phydrv = phydev->drv; int ret; lockdep_assert_held(&phydev->lock); diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 7fd9fe6a602b..7b1bc5fcef9b 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -22,7 +22,7 @@ struct gmii2rgmii { struct phy_device *phy_dev; - struct phy_driver *phy_drv; + const struct phy_driver *phy_drv; struct phy_driver conv_phy_drv; struct mdio_device *mdio; }; diff --git a/include/linux/phy.h b/include/linux/phy.h index a66f07d3f5f4..ad93f8b1b128 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -638,7 +638,7 @@ struct phy_device { /* Information about the PHY type */ /* And management functions */ - struct phy_driver *drv; + const struct phy_driver *drv; struct device_link *devlink; -- cgit v1.2.3 From b64691274f5d33fc9d93af73483162967f7ec5bb Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 3 Feb 2024 20:53:15 +0100 Subject: net: phy: add helper phy_advertise_eee_all Per default phylib preserves the EEE advertising at the time of phy probing. The EEE advertising can be changed from user space, in addition this helper allows to set the EEE advertising to all supported modes from drivers in kernel space. Suggested-by: Andrew Lunn Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20bfc471-aeeb-4ae4-ba09-7d6d4be6b86a@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 16 ++++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2eed8f03621d..839e42f9e16a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2777,6 +2777,22 @@ void phy_advertise_supported(struct phy_device *phydev) } EXPORT_SYMBOL(phy_advertise_supported); +/** + * phy_advertise_eee_all - Advertise all supported EEE modes + * @phydev: target phy_device struct + * + * Description: Per default phylib preserves the EEE advertising at the time of + * phy probing, which might be a subset of the supported EEE modes. Use this + * function when all supported EEE modes should be advertised. This does not + * trigger auto-negotiation, so must be called before phy_start()/ + * phylink_start() which will start auto-negotiation. + */ +void phy_advertise_eee_all(struct phy_device *phydev) +{ + linkmode_copy(phydev->advertising_eee, phydev->supported_eee); +} +EXPORT_SYMBOL_GPL(phy_advertise_eee_all); + /** * phy_support_sym_pause - Enable support of symmetrical pause * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index ad93f8b1b128..fd8dbea9b4d9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1960,6 +1960,7 @@ int phy_get_rate_matching(struct phy_device *phydev, void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); +void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, -- cgit v1.2.3 From d160c66cda0ac8614adc53a5b5b0e6d6f1a05a5b Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 5 Feb 2024 12:30:22 +0200 Subject: net: Do not return value from init_dummy_netdev() init_dummy_netdev() always returns zero and all the callers do not check the returned value. Set the function to not return value, as it is not really used today. Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Reviewed-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240205103022.440946-1-amcohen@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- net/core/dev.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 118c40258d07..1845dd5043b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3198,7 +3198,7 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); -int init_dummy_netdev(struct net_device *dev); +void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, diff --git a/net/core/dev.c b/net/core/dev.c index 27ba057d06c4..e52e2888cccd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10345,7 +10345,7 @@ EXPORT_SYMBOL(register_netdevice); * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ -int init_dummy_netdev(struct net_device *dev) +void init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * are they aren't supposed to be taken by any of the @@ -10373,8 +10373,6 @@ int init_dummy_netdev(struct net_device *dev) * because users of this 'device' dont need to change * its refcount. */ - - return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); -- cgit v1.2.3 From c478db84c8544156b80c5e5d3a8c7840d557707a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Jan 2024 19:34:45 +0100 Subject: wifi: mac80211: refactor puncturing bitmap extraction Add a new inline helper function to ieee80211.h to extract the disabled subchannels bitmap from an EHT operation element, and use that in mac80211 where we do that. Link: https://msgid.link/20240129194108.d9f50dcec8d0.I8b08cbc2490a734fafcce0fa0fc328211ba6f10b@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 16 +++++++++++++++ net/mac80211/mlme.c | 52 ++++++++++++++++------------------------------- 2 files changed, 33 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a70388ae3a7b..d9d2c1253157 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3189,6 +3189,22 @@ ieee80211_eht_oper_size_ok(const u8 *data, u8 len) return len >= needed; } +/* must validate ieee80211_eht_oper_size_ok() first */ +static inline u16 +ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper) +{ + const struct ieee80211_eht_operation_info *info = + (const void *)eht_oper->optional; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) + return 0; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) + return 0; + + return get_unaligned_le16(info->optional); +} + #define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) struct ieee80211_bandwidth_indication { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index da202103faf0..74a15f18e7ee 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -813,36 +813,27 @@ again: } if (conn->mode >= IEEE80211_CONN_MODE_EHT) { - const struct ieee80211_eht_operation *eht_oper; + u16 bitmap; - eht_oper = elems->eht_operation; - - if (WARN_ON_ONCE(!eht_oper)) { + if (WARN_ON_ONCE(!elems->eht_operation)) { ret = -EINVAL; goto free; } - if (eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT && - eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) { - const struct ieee80211_eht_operation_info *info = - (void *)eht_oper->optional; - const u8 *disable_subchannel_bitmap = info->optional; - u16 bitmap; - - bitmap = get_unaligned_le16(disable_subchannel_bitmap); - if (!cfg80211_valid_disable_subchannel_bitmap(&bitmap, - &ap_chandef) || - (bitmap && - ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))) { - conn->mode = IEEE80211_CONN_MODE_HE; - conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, - conn->bw_limit, - IEEE80211_CONN_BW_LIMIT_160); - sdata_info(sdata, - "AP has invalid/unsupported puncturing, disabling EHT\n"); - } - /* FIXME: store puncturing bitmap */ + bitmap = ieee80211_eht_oper_dis_subchan_bitmap(elems->eht_operation); + + if (!cfg80211_valid_disable_subchannel_bitmap(&bitmap, + &ap_chandef) || + (bitmap && + ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))) { + conn->mode = IEEE80211_CONN_MODE_HE; + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_160); + sdata_info(sdata, + "AP has invalid/unsupported puncturing, disabling EHT\n"); } + /* FIXME: store puncturing bitmap */ } /* the mode can only decrease, so this must terminate */ @@ -5879,18 +5870,9 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link, u64 *changed) { struct ieee80211_local *local = link->sdata->local; - u16 bitmap = 0, extracted; - - if ((eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) && - (eht_oper->params & - IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) { - const struct ieee80211_eht_operation_info *info = - (void *)eht_oper->optional; - const u8 *disable_subchannel_bitmap = info->optional; - - bitmap = get_unaligned_le16(disable_subchannel_bitmap); - } + u16 bitmap, extracted; + bitmap = ieee80211_eht_oper_dis_subchan_bitmap(eht_oper); extracted = ieee80211_extract_dis_subch_bmap(eht_oper, &link->conf->chanreq.oper, bitmap); -- cgit v1.2.3 From b1344b1399daec9aca62bd0b2ea94874f5b8e126 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Jan 2024 20:04:56 +0100 Subject: wifi: mac80211: add/use ieee80211_get_sn() This will also be useful for MLO duplicate multicast detection, but add it already here and use it in one place that trivially converts. Link: https://msgid.link/20240129200456.f0ff49c80006.I850d2785ab1640e56e262d3ad7343b87f6962552@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 ++++++- net/mac80211/rx.c | 5 ++--- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9d2c1253157..b9367d5f04c4 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2023 Intel Corporation + * Copyright (c) 2018 - 2024 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -808,6 +808,11 @@ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr) hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG); } +static inline u16 ieee80211_get_sn(struct ieee80211_hdr *hdr) +{ + return le16_get_bits(hdr->seq_ctrl, IEEE80211_SCTL_SEQ); +} + struct ieee80211s_hdr { u8 flags; u8 ttl; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 76798e8057f7..53c4764dc1ed 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include @@ -1251,8 +1251,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - u16 sc = le16_to_cpu(hdr->seq_ctrl); - u16 mpdu_seq_num = (sc & IEEE80211_SCTL_SEQ) >> 4; + u16 mpdu_seq_num = ieee80211_get_sn(hdr); u16 head_seq_num, buf_size; int index; bool ret = true; -- cgit v1.2.3 From 676259100cf3a81dd2d47918b36edb237986b9df Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Jan 2024 20:04:57 +0100 Subject: wifi: mac80211: implement MLO multicast deduplication If the vif is an MLD then it may receive multicast from different links, and should drop those frames according to the SN. Implement that. Link: https://msgid.link/20240129200456.693b77d14b44.I491846f2bea0058c14eab6422962c10bfae9b675@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 +++++ net/mac80211/ieee80211_i.h | 4 +++- net/mac80211/mlme.c | 3 +++ net/mac80211/rx.c | 22 ++++++++++++++++++++-- 4 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b9367d5f04c4..e9078143b822 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -191,6 +191,11 @@ static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } +static inline bool ieee80211_sn_less_eq(u16 sn1, u16 sn2) +{ + return ((sn2 - sn1) & IEEE80211_SN_MASK) <= (IEEE80211_SN_MODULO >> 1); +} + static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2) { return (sn1 + sn2) & IEEE80211_SN_MASK; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 534cac3fc8df..46b517cf47ea 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #ifndef IEEE80211_I_H @@ -523,6 +523,8 @@ struct ieee80211_if_managed { unsigned int flags; + u16 mcast_seq_last; + bool status_acked; bool status_received; __le16 status_fc; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 4eaf5c10efdb..35dda5982854 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3351,6 +3351,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); ieee80211_vif_set_links(sdata, 0, 0); + + ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; } static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) @@ -7512,6 +7514,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) spin_lock_init(&ifmgd->teardown_lock); ifmgd->teardown_skb = NULL; ifmgd->orig_teardown_skb = NULL; + ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; } static void ieee80211_recalc_smps_work(struct wiphy *wiphy, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 53c4764dc1ed..9902ea69af0a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1434,13 +1434,31 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || - ieee80211_is_any_nullfunc(hdr->frame_control) || - is_multicast_ether_addr(hdr->addr1)) + ieee80211_is_any_nullfunc(hdr->frame_control)) return RX_CONTINUE; if (!rx->sta) return RX_CONTINUE; + if (unlikely(is_multicast_ether_addr(hdr->addr1))) { + struct ieee80211_sub_if_data *sdata = rx->sdata; + u16 sn = ieee80211_get_sn(hdr); + + if (!ieee80211_is_data_present(hdr->frame_control)) + return RX_CONTINUE; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + sdata->vif.type != NL80211_IFTYPE_STATION) + return RX_CONTINUE; + + if (sdata->u.mgd.mcast_seq_last != IEEE80211_SN_MODULO && + ieee80211_sn_less_eq(sn, sdata->u.mgd.mcast_seq_last)) + return RX_DROP_U_DUP; + + sdata->u.mgd.mcast_seq_last = sn; + return RX_CONTINUE; + } + if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { I802_DEBUG_INC(rx->local->dot11FrameDuplicateCount); -- cgit v1.2.3 From 6239da18d2f947523a80fb1f85f8d8a13d1726c1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Jan 2024 20:19:28 +0100 Subject: wifi: mac80211: adjust EHT capa when lowering bandwidth If intending to associate with a lower bandwidth, remove capabilities related to 320 MHz from the EHT capabilities element. Also change the EHT MCS-NSS set accordingly: if just reducing 320->160 or similar the format doesn't change, just cut off the last bytes. If changing from higher bandwidth to 20 MHz only EHT STA, adjust the format. Note that this also requires adjusting the caller in mlme.c since the data written can now be shorter than it determined. We need to clean all that up. Since the other callers pass NULL for the conn limit, we don't need to change things there. Link: https://msgid.link/20240129202041.b5f6df108c77.I0d8ea04079c61cb3744cc88625eeaf0d4776dc2b@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 ++ net/mac80211/ieee80211_i.h | 3 +- net/mac80211/mesh.c | 3 +- net/mac80211/mlme.c | 15 ++++-- net/mac80211/tdls.c | 5 +- net/mac80211/util.c | 114 ++++++++++++++++++++++++++++++++++----------- 6 files changed, 106 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e9078143b822..e4322238f273 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3060,6 +3060,9 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 #define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 #define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 #define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 44400ce9a0b1..43c55ea6349c 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2652,7 +2652,8 @@ void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata); -u8 *ieee80211_ie_build_eht_cap(u8 *pos, +u8 *ieee80211_ie_build_eht_cap(const struct ieee80211_conn_settings *conn, + u8 *pos, const struct ieee80211_sta_he_cap *he_cap, const struct ieee80211_sta_eht_cap *eht_cap, u8 *end, diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 9fd209e4ca19..000fa9484b4e 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -668,7 +668,8 @@ int mesh_add_eht_cap_ie(struct ieee80211_sub_if_data *sdata, return -ENOMEM; pos = skb_put(skb, ie_len); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + ie_len, false); + ieee80211_ie_build_eht_cap(NULL, pos, he_cap, eht_cap, pos + ie_len, + false); return 0; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9a0331d914d3..bbc7894ccad0 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1072,9 +1072,10 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, static void ieee80211_add_eht_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_supported_band *sband) + struct ieee80211_supported_band *sband, + const struct ieee80211_conn_settings *conn) { - u8 *pos; + u8 *pos, *pre_eht_pos; const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; u8 eht_cap_size; @@ -1097,8 +1098,11 @@ static void ieee80211_add_eht_ie(struct ieee80211_sub_if_data *sdata, ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); pos = skb_put(skb, eht_cap_size); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + eht_cap_size, - false); + pre_eht_pos = pos; + pos = ieee80211_ie_build_eht_cap(conn, pos, he_cap, eht_cap, + pos + eht_cap_size, false); + /* trim excess if any */ + skb_trim(skb, skb->len - (pre_eht_pos + eht_cap_size - pos)); } static void ieee80211_assoc_add_rates(struct sk_buff *skb, @@ -1453,7 +1457,8 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, present_elems = NULL; if (assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_EHT) - ieee80211_add_eht_ie(sdata, skb, sband); + ieee80211_add_eht_ie(sdata, skb, sband, + &assoc_data->link[link_id].conn); if (sband->band == NL80211_BAND_S1GHZ) { ieee80211_add_aid_request_ie(sdata, skb); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 0f4aa42e070f..57673f27daf4 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -6,7 +6,7 @@ * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH * Copyright 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2019, 2021-2023 Intel Corporation + * Copyright (C) 2019, 2021-2024 Intel Corporation */ #include @@ -604,7 +604,8 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); pos = skb_put(skb, cap_size); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + cap_size, false); + ieee80211_ie_build_eht_cap(NULL, pos, he_cap, eht_cap, + pos + cap_size, false); } /* add any remaining IEs */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e9a7978d47d4..5224c22b1afc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2250,7 +2250,8 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE | IEEE80211_CHAN_NO_EHT)) { - pos = ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, end, + pos = ieee80211_ie_build_eht_cap(NULL, pos, he_cap, eht_cap, + end, sdata->vif.type == NL80211_IFTYPE_AP); if (!pos) goto out_err; @@ -3294,6 +3295,24 @@ u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata) he_cap->he_cap_elem.phy_cap_info); } +static void +ieee80211_get_adjusted_he_cap(const struct ieee80211_conn_settings *conn, + const struct ieee80211_sta_he_cap *he_cap, + struct ieee80211_he_cap_elem *elem) +{ + *elem = he_cap->he_cap_elem; + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) + elem->phy_cap_info[0] &= + ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G); + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160) + elem->phy_cap_info[0] &= + ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G); +} + u8 *ieee80211_ie_build_he_cap(const struct ieee80211_conn_settings *conn, const struct ieee80211_sta_he_cap *he_cap, u8 *pos, u8 *end) @@ -3307,25 +3326,11 @@ u8 *ieee80211_ie_build_he_cap(const struct ieee80211_conn_settings *conn, conn = &ieee80211_conn_settings_unlimited; /* Make sure we have place for the IE */ - /* - * TODO: the 1 added is because this temporarily is under the EXTENSION - * IE. Get rid of it when it moves. - */ if (!he_cap) return orig_pos; /* modify on stack first to calculate 'n' and 'ie_len' correctly */ - elem = he_cap->he_cap_elem; - - if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) - elem.phy_cap_info[0] &= - ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G); - - if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160) - elem.phy_cap_info[0] &= - ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G); + ieee80211_get_adjusted_he_cap(conn, he_cap, &elem); n = ieee80211_he_mcs_nss_size(&elem); ie_len = 2 + 1 + @@ -5096,25 +5101,65 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata) return 0; } -u8 *ieee80211_ie_build_eht_cap(u8 *pos, +u8 *ieee80211_ie_build_eht_cap(const struct ieee80211_conn_settings *conn, + u8 *pos, const struct ieee80211_sta_he_cap *he_cap, const struct ieee80211_sta_eht_cap *eht_cap, - u8 *end, - bool for_ap) + u8 *end, bool for_ap) { + struct ieee80211_eht_cap_elem_fixed fixed, *out; + struct ieee80211_he_cap_elem he; u8 mcs_nss_len, ppet_len; + u8 orig_mcs_nss_len; u8 ie_len; u8 *orig_pos = pos; + if (!conn) + conn = &ieee80211_conn_settings_unlimited; + /* Make sure we have place for the IE */ if (!he_cap || !eht_cap) return orig_pos; - mcs_nss_len = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, - &eht_cap->eht_cap_elem, - for_ap); + orig_mcs_nss_len = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, + &eht_cap->eht_cap_elem, + for_ap); + + ieee80211_get_adjusted_he_cap(conn, he_cap, &he); + + fixed = eht_cap->eht_cap_elem; + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_80) + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ; + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160) { + fixed.phy_cap_info[1] &= + ~IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK; + fixed.phy_cap_info[2] &= + ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK; + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ; + } + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_320) { + fixed.phy_cap_info[0] &= + ~IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ; + fixed.phy_cap_info[1] &= + ~IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK; + fixed.phy_cap_info[2] &= + ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK; + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ; + } + + if (conn->bw_limit == IEEE80211_CONN_BW_LIMIT_20) + fixed.phy_cap_info[0] &= + ~IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ; + + mcs_nss_len = ieee80211_eht_mcs_nss_size(&he, &fixed, for_ap); ppet_len = ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], - eht_cap->eht_cap_elem.phy_cap_info); + fixed.phy_cap_info); ie_len = 2 + 1 + sizeof(eht_cap->eht_cap_elem) + mcs_nss_len + ppet_len; if ((end - pos) < ie_len) @@ -5124,12 +5169,25 @@ u8 *ieee80211_ie_build_eht_cap(u8 *pos, *pos++ = ie_len - 2; *pos++ = WLAN_EID_EXT_EHT_CAPABILITY; - /* Fixed data */ - memcpy(pos, &eht_cap->eht_cap_elem, sizeof(eht_cap->eht_cap_elem)); - pos += sizeof(eht_cap->eht_cap_elem); + out = (void *)pos; + *out = fixed; + pos += sizeof(*out); - memcpy(pos, &eht_cap->eht_mcs_nss_supp, mcs_nss_len); - pos += mcs_nss_len; + if (mcs_nss_len == 4 && orig_mcs_nss_len != 4) { + /* + * If the (non-AP) STA became 20 MHz only, then convert from + * <=80 to 20-MHz-only format, where MCSes are indicated in + * the groups 0-7, 8-9, 10-11, 12-13 rather than just 0-9, + * 10-11, 12-13. Thus, use 0-9 for 0-7 and 8-9. + */ + *pos++ = eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs9_max_nss; + *pos++ = eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs9_max_nss; + *pos++ = eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs11_max_nss; + *pos++ = eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs13_max_nss; + } else { + memcpy(pos, &eht_cap->eht_mcs_nss_supp, mcs_nss_len); + pos += mcs_nss_len; + } if (ppet_len) { memcpy(pos, &eht_cap->eht_ppe_thres, ppet_len); -- cgit v1.2.3 From e3caf184107a4e2e196528b98b218ddc41e4cb8c Mon Sep 17 00:00:00 2001 From: Jinjian Song Date: Mon, 5 Feb 2024 18:22:27 +0800 Subject: wwan: core: Add WWAN fastboot port type Add a new WWAN port that connects to the device fastboot protocol interface. Signed-off-by: Jinjian Song Signed-off-by: David S. Miller --- drivers/net/wwan/wwan_core.c | 4 ++++ include/linux/wwan.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 72e01e550a16..2ed20b20e7fc 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -328,6 +328,10 @@ static const struct { .name = "XMMRPC", .devsuf = "xmmrpc", }, + [WWAN_PORT_FASTBOOT] = { + .name = "FASTBOOT", + .devsuf = "fastboot", + }, }; static ssize_t type_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 01fa15506286..170fdee6339c 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -16,6 +16,7 @@ * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol * @WWAN_PORT_XMMRPC: Control protocol for Intel XMM modems + * @WWAN_PORT_FASTBOOT: Fastboot protocol control * * @WWAN_PORT_MAX: Highest supported port types * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type @@ -28,6 +29,7 @@ enum wwan_port_type { WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, WWAN_PORT_XMMRPC, + WWAN_PORT_FASTBOOT, /* Add new port types above this line */ -- cgit v1.2.3 From 471e8fd3afcef5a9f9089f0bd21965ad9ba35c91 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Tue, 6 Feb 2024 18:31:06 +0100 Subject: net: phy: add devm/of_phy_package_join helper Add devm/of_phy_package_join helper to join PHYs in a PHY package. These are variant of the manual phy_package_join with the difference that these will use DT nodes to derive the base_addr instead of manually passing an hardcoded value. An additional value is added in phy_package_shared, "np" to reference the PHY package node pointer in specific PHY driver probe_once and config_init_once functions to make use of additional specific properties defined in the PHY package node in DT. The np value is filled only with of_phy_package_join if a valid PHY package node is found. A valid PHY package node must have the node name set to "ethernet-phy-package". Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 96 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 6 +++ 2 files changed, 102 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2e7d5bfb338e..71d48152e8d5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1712,6 +1712,7 @@ int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size) shared->priv_size = priv_size; } shared->base_addr = base_addr; + shared->np = NULL; refcount_set(&shared->refcnt, 1); bus->shared[base_addr] = shared; } else { @@ -1734,6 +1735,63 @@ err_unlock: } EXPORT_SYMBOL_GPL(phy_package_join); +/** + * of_phy_package_join - join a common PHY group in PHY package + * @phydev: target phy_device struct + * @priv_size: if non-zero allocate this amount of bytes for private data + * + * This is a variant of phy_package_join for PHY package defined in DT. + * + * The parent node of the @phydev is checked as a valid PHY package node + * structure (by matching the node name "ethernet-phy-package") and the + * base_addr for the PHY package is passed to phy_package_join. + * + * With this configuration the shared struct will also have the np value + * filled to use additional DT defined properties in PHY specific + * probe_once and config_init_once PHY package OPs. + * + * Returns < 0 on error, 0 on success. Esp. calling phy_package_join() + * with the same cookie but a different priv_size is an error. Or a parent + * node is not detected or is not valid or doesn't match the expected node + * name for PHY package. + */ +int of_phy_package_join(struct phy_device *phydev, size_t priv_size) +{ + struct device_node *node = phydev->mdio.dev.of_node; + struct device_node *package_node; + u32 base_addr; + int ret; + + if (!node) + return -EINVAL; + + package_node = of_get_parent(node); + if (!package_node) + return -EINVAL; + + if (!of_node_name_eq(package_node, "ethernet-phy-package")) { + ret = -EINVAL; + goto exit; + } + + if (of_property_read_u32(package_node, "reg", &base_addr)) { + ret = -EINVAL; + goto exit; + } + + ret = phy_package_join(phydev, base_addr, priv_size); + if (ret) + goto exit; + + phydev->shared->np = package_node; + + return 0; +exit: + of_node_put(package_node); + return ret; +} +EXPORT_SYMBOL_GPL(of_phy_package_join); + /** * phy_package_leave - leave a common PHY group * @phydev: target phy_device struct @@ -1750,6 +1808,10 @@ void phy_package_leave(struct phy_device *phydev) if (!shared) return; + /* Decrease the node refcount on leave if present */ + if (shared->np) + of_node_put(shared->np); + if (refcount_dec_and_mutex_lock(&shared->refcnt, &bus->shared_lock)) { bus->shared[shared->base_addr] = NULL; mutex_unlock(&bus->shared_lock); @@ -1802,6 +1864,40 @@ int devm_phy_package_join(struct device *dev, struct phy_device *phydev, } EXPORT_SYMBOL_GPL(devm_phy_package_join); +/** + * devm_of_phy_package_join - resource managed of_phy_package_join() + * @dev: device that is registering this PHY package + * @phydev: target phy_device struct + * @priv_size: if non-zero allocate this amount of bytes for private data + * + * Managed of_phy_package_join(). Shared storage fetched by this function, + * phy_package_leave() is automatically called on driver detach. See + * of_phy_package_join() for more information. + */ +int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, + size_t priv_size) +{ + struct phy_device **ptr; + int ret; + + ptr = devres_alloc(devm_phy_package_leave, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + ret = of_phy_package_join(phydev, priv_size); + + if (!ret) { + *ptr = phydev; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return ret; +} +EXPORT_SYMBOL_GPL(devm_of_phy_package_join); + /** * phy_detach - detach a PHY device from its network device * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index fd8dbea9b4d9..cbd49418b819 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -329,6 +329,7 @@ struct mdio_bus_stats { * struct phy_package_shared - Shared information in PHY packages * @base_addr: Base PHY address of PHY package used to combine PHYs * in one package and for offset calculation of phy_package_read/write + * @np: Pointer to the Device Node if PHY package defined in DT * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv @@ -340,6 +341,8 @@ struct mdio_bus_stats { */ struct phy_package_shared { u8 base_addr; + /* With PHY package defined in DT this points to the PHY package node */ + struct device_node *np; refcount_t refcnt; unsigned long flags; size_t priv_size; @@ -2000,9 +2003,12 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); +int of_phy_package_join(struct phy_device *phydev, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int base_addr, size_t priv_size); +int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, + size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit v1.2.3 From 9b1d5e055508393561e26bd1720f4c2639b03b1a Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Tue, 6 Feb 2024 18:31:09 +0100 Subject: net: phy: provide whether link has changed in c37_read_status Some PHY driver might require additional regs call after genphy_c37_read_status() is called. Expand genphy_c37_read_status to provide a bool wheather the link has changed or not to permit PHY driver to skip additional regs call if nothing has changed. Every user of genphy_c37_read_status() is updated with the new additional bool. Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 3 ++- drivers/net/phy/phy_device.c | 11 +++++++++-- drivers/net/phy/qcom/at803x.c | 3 ++- include/linux/phy.h | 2 +- 4 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 312a8bb35d78..370e4ed45098 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -665,10 +665,11 @@ static int bcm54616s_config_aneg(struct phy_device *phydev) static int bcm54616s_read_status(struct phy_device *phydev) { struct bcm54616s_phy_priv *priv = phydev->priv; + bool changed; int err; if (priv->mode_1000bx_en) - err = genphy_c37_read_status(phydev); + err = genphy_c37_read_status(phydev, &changed); else err = genphy_read_status(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 71d48152e8d5..9f37c0bfbf8d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2621,12 +2621,15 @@ EXPORT_SYMBOL(genphy_read_status); /** * genphy_c37_read_status - check the link status and update current link state * @phydev: target phy_device struct + * @changed: pointer where to store if link changed * * Description: Check the link, then figure out the current state * by comparing what we advertise with what the link partner * advertises. This function is for Clause 37 1000Base-X mode. + * + * If link has changed, @changed is set to true, false otherwise. */ -int genphy_c37_read_status(struct phy_device *phydev) +int genphy_c37_read_status(struct phy_device *phydev, bool *changed) { int lpa, err, old_link = phydev->link; @@ -2636,9 +2639,13 @@ int genphy_c37_read_status(struct phy_device *phydev) return err; /* why bother the PHY if nothing can have changed */ - if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) { + *changed = false; return 0; + } + /* Signal link has changed */ + *changed = true; phydev->duplex = DUPLEX_UNKNOWN; phydev->pause = 0; phydev->asym_pause = 0; diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 3e3ee4c1d4bc..4717c59d51d0 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -912,9 +912,10 @@ static int at8031_config_intr(struct phy_device *phydev) static int at8031_read_status(struct phy_device *phydev) { struct at803x_priv *priv = phydev->priv; + bool changed; if (priv->is_1000basex) - return genphy_c37_read_status(phydev); + return genphy_c37_read_status(phydev, &changed); return at803x_read_status(phydev); } diff --git a/include/linux/phy.h b/include/linux/phy.h index cbd49418b819..2249cdb5957a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1876,7 +1876,7 @@ int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, /* Clause 37 */ int genphy_c37_config_aneg(struct phy_device *phydev); -int genphy_c37_read_status(struct phy_device *phydev); +int genphy_c37_read_status(struct phy_device *phydev, bool *changed); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From 68bc61c26cacf152baf905786b5949769700f40d Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 7 Feb 2024 13:26:17 +0100 Subject: bpf: Allow compiler to inline most of bpf_local_storage_lookup() In various performance profiles of kernels with BPF programs attached, bpf_local_storage_lookup() appears as a significant portion of CPU cycles spent. To enable the compiler generate more optimal code, turn bpf_local_storage_lookup() into a static inline function, where only the cache insertion code path is outlined Notably, outlining cache insertion helps avoid bloating callers by duplicating setting up calls to raw_spin_{lock,unlock}_irqsave() (on architectures which do not inline spin_lock/unlock, such as x86), which would cause the compiler produce worse code by deciding to outline otherwise inlinable functions. The call overhead is neutral, because we make 2 calls either way: either calling raw_spin_lock_irqsave() and raw_spin_unlock_irqsave(); or call __bpf_local_storage_insert_cache(), which calls raw_spin_lock_irqsave(), followed by a tail-call to raw_spin_unlock_irqsave() where the compiler can perform TCO and (in optimized uninstrumented builds) turns it into a plain jump. The call to __bpf_local_storage_insert_cache() can be elided entirely if cacheit_lockit is a false constant expression. Based on results from './benchs/run_bench_local_storage.sh' (21 trials, reboot between each trial; x86 defconfig + BPF, clang 16) this produces improvements in throughput and latency in the majority of cases, with an average (geomean) improvement of 8%: +---- Hashmap Control -------------------- | | + num keys: 10 | : | | +-+ hashmap (control) sequential get +----------------------+---------------------- | +- hits throughput | 14.789 M ops/s | 14.745 M ops/s ( ~ ) | +- hits latency | 67.679 ns/op | 67.879 ns/op ( ~ ) | +- important_hits throughput | 14.789 M ops/s | 14.745 M ops/s ( ~ ) | | + num keys: 1000 | : | | +-+ hashmap (control) sequential get +----------------------+---------------------- | +- hits throughput | 12.233 M ops/s | 12.170 M ops/s ( ~ ) | +- hits latency | 81.754 ns/op | 82.185 ns/op ( ~ ) | +- important_hits throughput | 12.233 M ops/s | 12.170 M ops/s ( ~ ) | | + num keys: 10000 | : | | +-+ hashmap (control) sequential get +----------------------+---------------------- | +- hits throughput | 7.220 M ops/s | 7.204 M ops/s ( ~ ) | +- hits latency | 138.522 ns/op | 138.842 ns/op ( ~ ) | +- important_hits throughput | 7.220 M ops/s | 7.204 M ops/s ( ~ ) | | + num keys: 100000 | : | | +-+ hashmap (control) sequential get +----------------------+---------------------- | +- hits throughput | 5.061 M ops/s | 5.165 M ops/s (+2.1%) | +- hits latency | 198.483 ns/op | 194.270 ns/op (-2.1%) | +- important_hits throughput | 5.061 M ops/s | 5.165 M ops/s (+2.1%) | | + num keys: 4194304 | : | | +-+ hashmap (control) sequential get +----------------------+---------------------- | +- hits throughput | 2.864 M ops/s | 2.882 M ops/s ( ~ ) | +- hits latency | 365.220 ns/op | 361.418 ns/op (-1.0%) | +- important_hits throughput | 2.864 M ops/s | 2.882 M ops/s ( ~ ) | +---- Local Storage ---------------------- | | + num_maps: 1 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 33.005 M ops/s | 39.068 M ops/s (+18.4%) | +- hits latency | 30.300 ns/op | 25.598 ns/op (-15.5%) | +- important_hits throughput | 33.005 M ops/s | 39.068 M ops/s (+18.4%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 37.151 M ops/s | 44.926 M ops/s (+20.9%) | +- hits latency | 26.919 ns/op | 22.259 ns/op (-17.3%) | +- important_hits throughput | 37.151 M ops/s | 44.926 M ops/s (+20.9%) | | + num_maps: 10 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 32.288 M ops/s | 38.099 M ops/s (+18.0%) | +- hits latency | 30.972 ns/op | 26.248 ns/op (-15.3%) | +- important_hits throughput | 3.229 M ops/s | 3.810 M ops/s (+18.0%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 34.473 M ops/s | 41.145 M ops/s (+19.4%) | +- hits latency | 29.010 ns/op | 24.307 ns/op (-16.2%) | +- important_hits throughput | 12.312 M ops/s | 14.695 M ops/s (+19.4%) | | + num_maps: 16 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 32.524 M ops/s | 38.341 M ops/s (+17.9%) | +- hits latency | 30.748 ns/op | 26.083 ns/op (-15.2%) | +- important_hits throughput | 2.033 M ops/s | 2.396 M ops/s (+17.9%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 34.575 M ops/s | 41.338 M ops/s (+19.6%) | +- hits latency | 28.925 ns/op | 24.193 ns/op (-16.4%) | +- important_hits throughput | 11.001 M ops/s | 13.153 M ops/s (+19.6%) | | + num_maps: 17 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 28.861 M ops/s | 32.756 M ops/s (+13.5%) | +- hits latency | 34.649 ns/op | 30.530 ns/op (-11.9%) | +- important_hits throughput | 1.700 M ops/s | 1.929 M ops/s (+13.5%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 31.529 M ops/s | 36.110 M ops/s (+14.5%) | +- hits latency | 31.719 ns/op | 27.697 ns/op (-12.7%) | +- important_hits throughput | 9.598 M ops/s | 10.993 M ops/s (+14.5%) | | + num_maps: 24 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 18.602 M ops/s | 19.937 M ops/s (+7.2%) | +- hits latency | 53.767 ns/op | 50.166 ns/op (-6.7%) | +- important_hits throughput | 0.776 M ops/s | 0.831 M ops/s (+7.2%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 21.718 M ops/s | 23.332 M ops/s (+7.4%) | +- hits latency | 46.047 ns/op | 42.865 ns/op (-6.9%) | +- important_hits throughput | 6.110 M ops/s | 6.564 M ops/s (+7.4%) | | + num_maps: 32 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 14.118 M ops/s | 14.626 M ops/s (+3.6%) | +- hits latency | 70.856 ns/op | 68.381 ns/op (-3.5%) | +- important_hits throughput | 0.442 M ops/s | 0.458 M ops/s (+3.6%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 17.111 M ops/s | 17.906 M ops/s (+4.6%) | +- hits latency | 58.451 ns/op | 55.865 ns/op (-4.4%) | +- important_hits throughput | 4.776 M ops/s | 4.998 M ops/s (+4.6%) | | + num_maps: 100 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 5.281 M ops/s | 5.528 M ops/s (+4.7%) | +- hits latency | 192.398 ns/op | 183.059 ns/op (-4.9%) | +- important_hits throughput | 0.053 M ops/s | 0.055 M ops/s (+4.9%) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 6.265 M ops/s | 6.498 M ops/s (+3.7%) | +- hits latency | 161.436 ns/op | 152.877 ns/op (-5.3%) | +- important_hits throughput | 1.636 M ops/s | 1.697 M ops/s (+3.7%) | | + num_maps: 1000 | : | | +-+ local_storage cache sequential get +----------------------+---------------------- | +- hits throughput | 0.355 M ops/s | 0.354 M ops/s ( ~ ) | +- hits latency | 2826.538 ns/op | 2827.139 ns/op ( ~ ) | +- important_hits throughput | 0.000 M ops/s | 0.000 M ops/s ( ~ ) | : | : | | +-+ local_storage cache interleaved get +----------------------+---------------------- | +- hits throughput | 0.404 M ops/s | 0.403 M ops/s ( ~ ) | +- hits latency | 2481.190 ns/op | 2487.555 ns/op ( ~ ) | +- important_hits throughput | 0.102 M ops/s | 0.101 M ops/s ( ~ ) The on_lookup test in {cgrp,task}_ls_recursion.c is removed because the bpf_local_storage_lookup is no longer traceable and adding tracepoint will make the compiler generate worse code: https://lore.kernel.org/bpf/ZcJmok64Xqv6l4ZS@elver.google.com/ Signed-off-by: Marco Elver Cc: Martin KaFai Lau Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20240207122626.3508658-1-elver@google.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf_local_storage.h | 30 ++++++++++++- kernel/bpf/bpf_local_storage.c | 52 ++++++---------------- .../selftests/bpf/prog_tests/task_local_storage.c | 6 --- .../selftests/bpf/progs/cgrp_ls_recursion.c | 26 ----------- .../selftests/bpf/progs/task_ls_recursion.c | 17 ------- 5 files changed, 41 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 173ec7f43ed1..dcddb0aef7d8 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -129,10 +129,36 @@ bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache, bool bpf_ma); -struct bpf_local_storage_data * +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); +/* If cacheit_lockit is false, this lookup function is lockless */ +static inline struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, - bool cacheit_lockit); + bool cacheit_lockit) +{ + struct bpf_local_storage_data *sdata; + struct bpf_local_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], + bpf_rcu_lock_held()); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &local_storage->list, snode, + rcu_read_lock_trace_held()) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + if (cacheit_lockit) + __bpf_local_storage_insert_cache(local_storage, smap, selem); + return SDATA(selem); +} void bpf_local_storage_destroy(struct bpf_local_storage *local_storage); diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 146824cc9689..bdea1a459153 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -414,47 +414,21 @@ void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) bpf_selem_unlink_storage(selem, reuse_now); } -/* If cacheit_lockit is false, this lookup function is lockless */ -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit) +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_local_storage_data *sdata; - struct bpf_local_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], - bpf_rcu_lock_held()); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode, - rcu_read_lock_trace_held()) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - unsigned long flags; - - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next bpf_local_storage_lookup(). - */ - raw_spin_lock_irqsave(&local_storage->lock, flags); - if (selem_linked_to_storage(selem)) - rcu_assign_pointer(local_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); - } + unsigned long flags; - return sdata; + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_irqsave(&local_storage->lock, flags); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c index ea8537c54413..c33c05161a9e 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c @@ -117,12 +117,6 @@ static void test_recursion(void) ASSERT_OK(err, "lookup map_b"); ASSERT_EQ(value, 100, "map_b value"); - prog_fd = bpf_program__fd(skel->progs.on_lookup); - memset(&info, 0, sizeof(info)); - err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); - ASSERT_OK(err, "get prog info"); - ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion"); - prog_fd = bpf_program__fd(skel->progs.on_update); memset(&info, 0, sizeof(info)); err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c index 610c2427fd93..3500e4b69ebe 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c @@ -27,32 +27,6 @@ bool is_cgroup1 = 0; struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym; void bpf_cgroup_release(struct cgroup *cgrp) __ksym; -static void __on_lookup(struct cgroup *cgrp) -{ - bpf_cgrp_storage_delete(&map_a, cgrp); - bpf_cgrp_storage_delete(&map_b, cgrp); -} - -SEC("fentry/bpf_local_storage_lookup") -int BPF_PROG(on_lookup) -{ - struct task_struct *task = bpf_get_current_task_btf(); - struct cgroup *cgrp; - - if (is_cgroup1) { - cgrp = bpf_task_get_cgroup1(task, target_hid); - if (!cgrp) - return 0; - - __on_lookup(cgrp); - bpf_cgroup_release(cgrp); - return 0; - } - - __on_lookup(task->cgroups->dfl_cgrp); - return 0; -} - static void __on_update(struct cgroup *cgrp) { long *ptr; diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c index 4542dc683b44..f1853c38aada 100644 --- a/tools/testing/selftests/bpf/progs/task_ls_recursion.c +++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c @@ -27,23 +27,6 @@ struct { __type(value, long); } map_b SEC(".maps"); -SEC("fentry/bpf_local_storage_lookup") -int BPF_PROG(on_lookup) -{ - struct task_struct *task = bpf_get_current_task_btf(); - - if (!test_pid || task->pid != test_pid) - return 0; - - /* The bpf_task_storage_delete will call - * bpf_local_storage_lookup. The prog->active will - * stop the recursion. - */ - bpf_task_storage_delete(&map_a, task); - bpf_task_storage_delete(&map_b, task); - return 0; -} - SEC("fentry/bpf_local_storage_update") int BPF_PROG(on_update) { -- cgit v1.2.3 From 178c54666f9c4d2f49f2ea661d0c11b52f0ed190 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 6 Feb 2024 23:01:02 -0800 Subject: bpf: Mark bpf_spin_{lock,unlock}() helpers with notrace correctly Currently tracing is supposed not to allow for bpf_spin_{lock,unlock}() helper calls. This is to prevent deadlock for the following cases: - there is a prog (prog-A) calling bpf_spin_{lock,unlock}(). - there is a tracing program (prog-B), e.g., fentry, attached to bpf_spin_lock() and/or bpf_spin_unlock(). - prog-B calls bpf_spin_{lock,unlock}(). For such a case, when prog-A calls bpf_spin_{lock,unlock}(), a deadlock will happen. The related source codes are below in kernel/bpf/helpers.c: notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) notrace is supposed to prevent fentry prog from attaching to bpf_spin_{lock,unlock}(). But actually this is not the case and fentry prog can successfully attached to bpf_spin_lock(). Siddharth Chintamaneni reported the issue in [1]. The following is the macro definition for above BPF_CALL_1: #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) The notrace attribute is actually applied to the static always_inline function ____bpf_spin_{lock,unlock}(). The actual callback function bpf_spin_{lock,unlock}() is not marked with notrace, hence allowing fentry prog to attach to two helpers, and this may cause the above mentioned deadlock. Siddharth Chintamaneni actually has a reproducer in [2]. To fix the issue, a new macro NOTRACE_BPF_CALL_1 is introduced which will add notrace attribute to the original function instead of the hidden always_inline function and this fixed the problem. [1] https://lore.kernel.org/bpf/CAE5sdEigPnoGrzN8WU7Tx-h-iFuMZgW06qp0KHWtpvoXxf1OAQ@mail.gmail.com/ [2] https://lore.kernel.org/bpf/CAE5sdEg6yUc_Jz50AnUXEEUh6O73yQ1Z6NV2srJnef0ZrQkZew@mail.gmail.com/ Fixes: d83525ca62cf ("bpf: introduce bpf_spin_lock") Signed-off-by: Yonghong Song Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240207070102.335167-1-yonghong.song@linux.dev --- include/linux/filter.h | 21 ++++++++++++--------- kernel/bpf/helpers.c | 4 ++-- 2 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index fee070b9826e..36cc29a2934c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -547,24 +547,27 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) -#define BPF_CALL_x(x, name, ...) \ +#define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -#define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) -#define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) -#define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) -#define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) -#define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) -#define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define __NOATTR +#define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) + +#define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3503949b4c1b..93edf730d288 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -334,7 +334,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -357,7 +357,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; -- cgit v1.2.3 From 77c0208e199ccb0986fb3612f2409c8cdcb036ad Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Thu, 8 Feb 2024 18:37:47 -0800 Subject: bpf: add btf pointer to struct bpf_ctx_arg_aux. Enable the providers to use types defined in a module instead of in the kernel (btf_vmlinux). Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240209023750.1153905-2-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 + kernel/bpf/btf.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1ebbee1d648e..3b7836f0a83e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1415,6 +1415,7 @@ struct bpf_jit_poke_descriptor { struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; + struct btf *btf; u32 btf_id; }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8e06d29961f1..cf100b5573ca 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6266,7 +6266,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = ctx_arg_info->reg_type; - info->btf = btf_vmlinux; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } -- cgit v1.2.3 From 6115a0aeef01aef152ad7738393aad11422bfb82 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Thu, 8 Feb 2024 18:37:48 -0800 Subject: bpf: Move __kfunc_param_match_suffix() to btf.c. Move __kfunc_param_match_suffix() to btf.c and rename it as btf_param_match_suffix(). It can be reused by bpf_struct_ops later. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240209023750.1153905-3-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/btf.h | 4 ++++ kernel/bpf/btf.c | 18 ++++++++++++++++++ kernel/bpf/verifier.c | 38 ++++++++++---------------------------- 3 files changed, 32 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 1ee8977b8c95..df76a14c64f6 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -495,6 +495,10 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix); + struct bpf_verifier_log; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index cf100b5573ca..447da964f217 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8904,3 +8904,21 @@ errout: } EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); #endif + +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix) +{ + int suffix_len = strlen(suffix), len; + const char *param_name; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len <= suffix_len) + return false; + param_name += len - suffix_len; + return !strncmp(param_name, suffix, suffix_len); +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ddaf09db1175..c92d6af7d975 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10682,24 +10682,6 @@ static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU_PROTECTED; } -static bool __kfunc_param_match_suffix(const struct btf *btf, - const struct btf_param *arg, - const char *suffix) -{ - int suffix_len = strlen(suffix), len; - const char *param_name; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < suffix_len) - return false; - param_name += len - suffix_len; - return !strncmp(param_name, suffix, suffix_len); -} - static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) @@ -10710,7 +10692,7 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__sz"); + return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, @@ -10723,47 +10705,47 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__szk"); + return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__opt"); + return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__k"); + return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__ign"); + return btf_param_match_suffix(btf, arg, "__ign"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__alloc"); + return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__uninit"); + return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__nullable"); + return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__str"); + return btf_param_match_suffix(btf, arg, "__str"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, -- cgit v1.2.3 From 1611603537a4b88cec7993f32b70c03113801a46 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Thu, 8 Feb 2024 18:37:49 -0800 Subject: bpf: Create argument information for nullable arguments. Collect argument information from the type information of stub functions to mark arguments of BPF struct_ops programs with PTR_MAYBE_NULL if they are nullable. A nullable argument is annotated by suffixing "__nullable" at the argument name of stub function. For nullable arguments, this patch sets a struct bpf_ctx_arg_aux to label their reg_type with PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL. This makes the verifier to check programs and ensure that they properly check the pointer. The programs should check if the pointer is null before accessing the pointed memory. The implementer of a struct_ops type should annotate the arguments that can be null. The implementer should define a stub function (empty) as a placeholder for each defined operator. The name of a stub function should be in the pattern "__". For example, for test_maybe_null of struct bpf_testmod_ops, it's stub function name should be "bpf_testmod_ops__test_maybe_null". You mark an argument nullable by suffixing the argument name with "__nullable" at the stub function. Since we already has stub functions for kCFI, we just reuse these stub functions with the naming convention mentioned earlier. These stub functions with the naming convention is only required if there are nullable arguments to annotate. For functions having not nullable arguments, stub functions are not necessary for the purpose of this patch. This patch will prepare a list of struct bpf_ctx_arg_aux, aka arg_info, for each member field of a struct_ops type. "arg_info" will be assigned to "prog->aux->ctx_arg_info" of BPF struct_ops programs in check_struct_ops_btf_id() so that it can be used by btf_ctx_access() later to set reg_type properly for the verifier. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240209023750.1153905-4-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 21 +++++ include/linux/btf.h | 2 + kernel/bpf/bpf_struct_ops.c | 213 +++++++++++++++++++++++++++++++++++++++++--- kernel/bpf/btf.c | 27 ++++++ kernel/bpf/verifier.c | 6 ++ 5 files changed, 257 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3b7836f0a83e..c7aa99b44dbd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1709,6 +1709,19 @@ struct bpf_struct_ops { struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; +/* Every member of a struct_ops type has an instance even a member is not + * an operator (function pointer). The "info" field will be assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the + * argument information required by the verifier to verify the program. + * + * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the + * corresponding entry for an given argument. + */ +struct bpf_struct_ops_arg_info { + struct bpf_ctx_arg_aux *info; + u32 cnt; +}; + struct bpf_struct_ops_desc { struct bpf_struct_ops *st_ops; @@ -1716,6 +1729,9 @@ struct bpf_struct_ops_desc { const struct btf_type *value_type; u32 type_id; u32 value_id; + + /* Collection of argument information for each member */ + struct bpf_struct_ops_arg_info *arg_info; }; enum bpf_struct_ops_state { @@ -1790,6 +1806,7 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc); #else #define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) @@ -1814,6 +1831,10 @@ static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struc { } +static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ +} + #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) diff --git a/include/linux/btf.h b/include/linux/btf.h index df76a14c64f6..cb96f6263638 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -498,6 +498,8 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) bool btf_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix); +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no); struct bpf_verifier_log; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index f98f580de77a..0d7be97a2411 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -116,17 +116,183 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } +#define MAYBE_NULL_SUFFIX "__nullable" +#define MAX_STUB_NAME 128 + +/* Return the type info of a stub function, if it exists. + * + * The name of a stub function is made up of the name of the struct_ops and + * the name of the function pointer member, separated by "__". For example, + * if the struct_ops type is named "foo_ops" and the function pointer + * member is named "bar", the stub function name would be "foo_ops__bar". + */ +static const struct btf_type * +find_stub_func_proto(const struct btf *btf, const char *st_op_name, + const char *member_name) +{ + char stub_func_name[MAX_STUB_NAME]; + const struct btf_type *func_type; + s32 btf_id; + int cp; + + cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s", + st_op_name, member_name); + if (cp >= MAX_STUB_NAME) { + pr_warn("Stub function name too long\n"); + return NULL; + } + btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC); + if (btf_id < 0) + return NULL; + func_type = btf_type_by_id(btf, btf_id); + if (!func_type) + return NULL; + + return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */ +} + +/* Prepare argument info for every nullable argument of a member of a + * struct_ops type. + * + * Initialize a struct bpf_struct_ops_arg_info according to type info of + * the arguments of a stub function. (Check kCFI for more information about + * stub functions.) + * + * Each member in the struct_ops type has a struct bpf_struct_ops_arg_info + * to provide an array of struct bpf_ctx_arg_aux, which in turn provides + * the information that used by the verifier to check the arguments of the + * BPF struct_ops program assigned to the member. Here, we only care about + * the arguments that are marked as __nullable. + * + * The array of struct bpf_ctx_arg_aux is eventually assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs and passed to the + * verifier. (See check_struct_ops_btf_id()) + * + * arg_info->info will be the list of struct bpf_ctx_arg_aux if success. If + * fails, it will be kept untouched. + */ +static int prepare_arg_info(struct btf *btf, + const char *st_ops_name, + const char *member_name, + const struct btf_type *func_proto, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + u32 arg_btf_id; + int offset; + + stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name); + if (!stub_func_proto) + return 0; + + /* Check if the number of arguments of the stub function is the same + * as the number of arguments of the function pointer. + */ + nargs = btf_type_vlen(func_proto); + if (nargs != btf_type_vlen(stub_func_proto)) { + pr_warn("the number of arguments of the stub function %s__%s does not match the number of arguments of the member %s of struct %s\n", + st_ops_name, member_name, member_name, st_ops_name); + return -EINVAL; + } + + if (!nargs) + return 0; + + args = btf_params(func_proto); + stub_args = btf_params(stub_func_proto); + + info_buf = kcalloc(nargs, sizeof(*info_buf), GFP_KERNEL); + if (!info_buf) + return -ENOMEM; + + /* Prepare info for every nullable argument */ + info = info_buf; + for (arg_no = 0; arg_no < nargs; arg_no++) { + /* Skip arguments that is not suffixed with + * "__nullable". + */ + if (!btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX)) + continue; + + /* Should be a pointer to struct */ + pointed_type = btf_type_resolve_ptr(btf, + args[arg_no].type, + &arg_btf_id); + if (!pointed_type || + !btf_type_is_struct(pointed_type)) { + pr_warn("stub function %s__%s has %s tagging to an unsupported type\n", + st_ops_name, member_name, MAYBE_NULL_SUFFIX); + goto err_out; + } + + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n", + st_ops_name, member_name, arg_no); + goto err_out; + } + + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n", + arg_no, st_ops_name, member_name); + goto err_out; + } + + /* Fill the information of the new argument */ + info->reg_type = + PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; + + info++; + info_cnt++; + } + + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } + + return 0; + +err_out: + kfree(info_buf); + + return -EINVAL; +} + +/* Clean up the arg_info in a struct bpf_struct_ops_desc. */ +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ + struct bpf_struct_ops_arg_info *arg_info; + int i; + + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); + + kfree(arg_info); +} + int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) { struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; + struct bpf_struct_ops_arg_info *arg_info; const struct btf_member *member; const struct btf_type *t; s32 type_id, value_id; char value_name[128]; const char *mname; - int i; + int i, err; if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= sizeof(value_name)) { @@ -160,6 +326,17 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!is_valid_value_type(btf, value_id, t, value_name)) return -EINVAL; + arg_info = kcalloc(btf_type_vlen(t), sizeof(*arg_info), + GFP_KERNEL); + if (!arg_info) + return -ENOMEM; + + st_ops_desc->arg_info = arg_info; + st_ops_desc->type = t; + st_ops_desc->type_id = type_id; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, value_id); + for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -167,40 +344,52 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!*mname) { pr_warn("anon member in struct %s is not supported\n", st_ops->name); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto errout; } if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto errout; } func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); - if (func_proto && - btf_distill_func_proto(log, btf, + if (!func_proto) + continue; + + if (btf_distill_func_proto(log, btf, func_proto, mname, &st_ops->func_models[i])) { pr_warn("Error in parsing func ptr %s in struct %s\n", mname, st_ops->name); - return -EINVAL; + err = -EINVAL; + goto errout; } + + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, + arg_info + i); + if (err) + goto errout; } if (st_ops->init(btf)) { pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); - return -EINVAL; + err = -EINVAL; + goto errout; } - st_ops_desc->type_id = type_id; - st_ops_desc->type = t; - st_ops_desc->value_id = value_id; - st_ops_desc->value_type = btf_type_by_id(btf, value_id); - return 0; + +errout: + bpf_struct_ops_desc_release(st_ops_desc); + + return err; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 447da964f217..efd9bc274be0 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1699,6 +1699,13 @@ static void btf_free_struct_meta_tab(struct btf *btf) static void btf_free_struct_ops_tab(struct btf *btf) { struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + u32 i; + + if (!tab) + return; + + for (i = 0; i < tab->cnt; i++) + bpf_struct_ops_desc_release(&tab->ops[i]); kfree(tab); btf->struct_ops_tab = NULL; @@ -6130,6 +6137,26 @@ static bool prog_args_trusted(const struct bpf_prog *prog) } } +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no) +{ + const struct btf_param *args; + const struct btf_type *t; + int off = 0, i; + u32 sz; + + args = btf_params(func_proto); + for (i = 0; i < arg_no; i++) { + t = btf_type_by_id(btf, args[i].type); + t = btf_resolve_size(btf, t, &sz); + if (IS_ERR(t)) + return PTR_ERR(t); + off += roundup(sz, 8); + } + + return off; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c92d6af7d975..72ca27f49616 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20419,6 +20419,12 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + /* btf_ctx_access() used this to provide argument type info */ + prog->aux->ctx_arg_info = + st_ops_desc->arg_info[member_idx].info; + prog->aux->ctx_arg_info_size = + st_ops_desc->arg_info[member_idx].cnt; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; -- cgit v1.2.3 From 32e18e7688c6847b0c9db073aafb00639ecf576c Mon Sep 17 00:00:00 2001 From: Oliver Crumrine Date: Fri, 9 Feb 2024 14:41:22 -0500 Subject: bpf: remove check in __cgroup_bpf_run_filter_skb Originally, this patch removed a redundant check in BPF_CGROUP_RUN_PROG_INET_EGRESS, as the check was already being done in the function it called, __cgroup_bpf_run_filter_skb. For v2, it was reccomended that I remove the check from __cgroup_bpf_run_filter_skb, and add the checks to the other macro that calls that function, BPF_CGROUP_RUN_PROG_INET_INGRESS. To sum it up, checking that the socket exists and that it is a full socket is now part of both macros BPF_CGROUP_RUN_PROG_INET_EGRESS and BPF_CGROUP_RUN_PROG_INET_INGRESS, and it is no longer part of the function they call, __cgroup_bpf_run_filter_skb. v3->v4: Fixed weird merge conflict. v2->v3: Sent to bpf-next instead of generic patch v1->v2: Addressed feedback about where check should be removed. Signed-off-by: Oliver Crumrine Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/7lv62yiyvmj5a7eozv2iznglpkydkdfancgmbhiptrgvgan5sy@3fl3onchgdz3 Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup.h | 3 ++- kernel/bpf/cgroup.c | 3 --- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a789266feac3..fb3c3e7181e6 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -196,7 +196,8 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ - cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS)) \ + cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS) && sk && \ + sk_fullsock(sk)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 98e0e3835b28..5a568bbbeaeb 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1364,9 +1364,6 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct cgroup *cgrp; int ret; - if (!sk || !sk_fullsock(sk)) - return 0; - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; -- cgit v1.2.3 From fb5b86cfd4ef21ea18966718f6bf6c8f1b9df12e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Feb 2024 15:32:18 -0800 Subject: bpf: simplify btf_get_prog_ctx_type() into btf_is_prog_ctx_type() Return result of btf_get_prog_ctx_type() is never used and callers only check NULL vs non-NULL case to determine if given type matches expected PTR_TO_CTX type. So rename function to `btf_is_prog_ctx_type()` and return a simple true/false. We'll use this simpler interface to handle kprobe program type's special typedef case in the next patch. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240212233221.2575350-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 17 ++++++++--------- kernel/bpf/btf.c | 27 +++++++++++++-------------- kernel/bpf/verifier.c | 2 +- 3 files changed, 22 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index cb96f6263638..f9e56fd12a9f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -531,10 +531,9 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); -const struct btf_type * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg); +bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg); int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); @@ -574,12 +573,12 @@ static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf { return NULL; } -static inline const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +static inline bool +btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) { - return NULL; + return false; } static inline int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index efd9bc274be0..405f95722905 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5694,10 +5694,9 @@ static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) return ctx_type->type; } -const struct btf_type * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) { const struct btf_type *ctx_type; const char *tname, *ctx_tname; @@ -5711,26 +5710,26 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - return NULL; + return false; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); - return NULL; + return false; } ctx_type = find_canonical_prog_ctx_type(prog_type); if (!ctx_type) { bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ - return NULL; + return false; } again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); - return NULL; + return false; } /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. @@ -5740,20 +5739,20 @@ again: * { // no fields of skb are ever used } */ if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ if (!btf_type_is_modifier(ctx_type)) - return NULL; + return false; while (btf_type_is_modifier(ctx_type)) ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } - return ctx_type; + return true; } /* forward declarations for arch-specific underlying types of @@ -5905,7 +5904,7 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, enum bpf_prog_type prog_type, int arg) { - if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) + if (!btf_is_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; return find_kern_ctx_type_id(prog_type); } @@ -7211,7 +7210,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) if (!btf_type_is_ptr(t)) goto skip_pointer; - if ((tags & ARG_TAG_CTX) || btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if ((tags & ARG_TAG_CTX) || btf_is_prog_ctx_type(log, btf, t, prog_type, i)) { if (tags & ~ARG_TAG_CTX) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 72ca27f49616..aa192dc735a9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11015,7 +11015,7 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ - if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) -- cgit v1.2.3 From 4d2bb0bfe8741a8778e0053f31a4e0f0cba80e8b Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:55 +0100 Subject: xdp: rely on skb pointer reference in do_xdp_generic and netif_receive_generic_xdp Rely on skb pointer reference instead of the skb pointer in do_xdp_generic and netif_receive_generic_xdp routine signatures. This is a preliminary patch to add multi-buff support for xdp running in generic mode where we will need to reallocate the skb to avoid linearization and we will need to make it visible to do_xdp_generic() caller. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/c09415b1f48c8620ef4d76deed35050a7bddf7c2.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/tun.c | 4 ++-- include/linux/netdevice.h | 2 +- net/core/dev.c | 16 +++++++++------- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b472f2c972d8..bc80fc1d576e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1926,7 +1926,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { - ret = do_xdp_generic(xdp_prog, skb); + ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); @@ -2516,7 +2516,7 @@ build: skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { - ret = do_xdp_generic(xdp_prog, skb); + ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 07cefa32eafa..a3f9c95da51e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3958,7 +3958,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index e19bdf1421e0..ffeb0e0279fe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4936,10 +4936,11 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, return act; } -static u32 netif_receive_generic_xdp(struct sk_buff *skb, +static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { + struct sk_buff *skb = *pskb; u32 act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should @@ -5020,24 +5021,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) { if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; - act = netif_receive_generic_xdp(skb, &xdp, xdp_prog); + act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: - err = xdp_do_generic_redirect(skb->dev, skb, + err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: - generic_xdp_tx(skb, xdp_prog); + generic_xdp_tx(*pskb, xdp_prog); break; } return XDP_DROP; @@ -5045,7 +5046,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) } return XDP_PASS; out_redir: - kfree_skb_reason(skb, SKB_DROP_REASON_XDP); + kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); @@ -5368,7 +5369,8 @@ another_round: int ret2; migrate_disable(); - ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); + ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), + &skb); migrate_enable(); if (ret2 != XDP_PASS) { -- cgit v1.2.3 From e6d5dbdd20aa6a86974af51deb9414cd2e7794cb Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:56 +0100 Subject: xdp: add multi-buff support for xdp running in generic mode Similar to native xdp, do not always linearize the skb in netif_receive_generic_xdp routine but create a non-linear xdp_buff to be processed by the eBPF program. This allow to add multi-buffer support for xdp running in generic mode. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/1044d6412b1c3e95b40d34993fd5f37cd2f319fd.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 ++ net/core/dev.c | 70 +++++++++++++++++++++++++++----------- net/core/skbuff.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 144 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2dde34c29203..def3d8689c3d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3446,6 +3446,8 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + struct bpf_prog *prog); bool napi_pp_put_page(struct page *page, bool napi_safe); static inline void diff --git a/net/core/dev.c b/net/core/dev.c index ffeb0e0279fe..2d02ca8a3da5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4874,6 +4874,12 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); + if (skb_is_nonlinear(skb)) { + skb_shinfo(skb)->xdp_frags_size = skb->data_len; + xdp_buff_set_frags_flag(xdp); + } else { + xdp_buff_clear_frags_flag(xdp); + } orig_data_end = xdp->data_end; orig_data = xdp->data; @@ -4903,6 +4909,14 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, skb->len += off; /* positive on grow, negative on shrink */ } + /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers + * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + */ + if (xdp_buff_has_frags(xdp)) + skb->data_len = skb_shinfo(skb)->xdp_frags_size; + else + skb->data_len = 0; + /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || @@ -4936,12 +4950,35 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, return act; } +static int +netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) +{ + struct sk_buff *skb = *pskb; + int err, hroom, troom; + + if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) + return 0; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + troom = skb->tail + skb->data_len - skb->end; + err = pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC); + if (err) + return err; + + return skb_linearize(skb); +} + static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; - u32 act = XDP_DROP; + u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. @@ -4949,41 +4986,36 @@ static u32 netif_receive_generic_xdp(struct sk_buff **pskb, if (skb_is_redirected(skb)) return XDP_PASS; - /* XDP packets must be linear and must have sufficient headroom - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also - * native XDP provides, thus we need to do it here as well. + /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM + * bytes. This is the guarantee that also native XDP provides, + * thus we need to do it here as well. */ + mac_len = skb->data - skb_mac_header(skb); + __skb_push(skb, mac_len); + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); - int troom = skb->tail + skb->data_len - skb->end; - - /* In case we have to go down the path and also linearize, - * then lets do the pskb_expand_head() work just once here. - */ - if (pskb_expand_head(skb, - hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, - troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) - goto do_drop; - if (skb_linearize(skb)) + if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } - act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + __skb_pull(*pskb, mac_len); + + act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); + bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(skb->dev, xdp_prog, act); + trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: - kfree_skb(skb); + kfree_skb(*pskb); break; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9e5eb47b4025..bdb94749f05d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -895,6 +895,97 @@ static bool is_pp_page(struct page *page) return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } +static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom) +{ +#if IS_ENABLED(CONFIG_PAGE_POOL) + u32 size, truesize, len, max_head_size, off; + struct sk_buff *skb = *pskb, *nskb; + int err, i, head_off; + void *data; + + /* XDP does not support fraglist so we need to linearize + * the skb. + */ + if (skb_has_frag_list(skb)) + return -EOPNOTSUPP; + + max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); + if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) + return -ENOMEM; + + size = min_t(u32, skb->len, max_head_size); + truesize = SKB_HEAD_ALIGN(size) + headroom; + data = page_pool_dev_alloc_va(pool, &truesize); + if (!data) + return -ENOMEM; + + nskb = napi_build_skb(data, truesize); + if (!nskb) { + page_pool_free_va(pool, data, true); + return -ENOMEM; + } + + skb_reserve(nskb, headroom); + skb_copy_header(nskb, skb); + skb_mark_for_recycle(nskb); + + err = skb_copy_bits(skb, 0, nskb->data, size); + if (err) { + consume_skb(nskb); + return err; + } + skb_put(nskb, size); + + head_off = skb_headroom(nskb) - skb_headroom(skb); + skb_headers_offset_update(nskb, head_off); + + off = size; + len = skb->len - off; + for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { + struct page *page; + u32 page_off; + + size = min_t(u32, len, PAGE_SIZE); + truesize = size; + + page = page_pool_dev_alloc(pool, &page_off, &truesize); + if (!data) { + consume_skb(nskb); + return -ENOMEM; + } + + skb_add_rx_frag(nskb, i, page, page_off, size, truesize); + err = skb_copy_bits(skb, off, page_address(page) + page_off, + size); + if (err) { + consume_skb(nskb); + return err; + } + + len -= size; + off += size; + } + + consume_skb(skb); + *pskb = nskb; + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + struct bpf_prog *prog) +{ + if (!prog->aux->xdp_has_frags) + return -EINVAL; + + return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); +} +EXPORT_SYMBOL(skb_cow_data_for_xdp); + #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page, bool napi_safe) { -- cgit v1.2.3 From 27accb3cc08a0ec4e348356774042d5fa5f30cce Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:57 +0100 Subject: veth: rely on skb_pp_cow_data utility routine Rely on skb_pp_cow_data utility routine and remove duplicated code. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/029cc14cce41cb242ee7efdcf32acc81f1ce4e9f.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/veth.c | 74 ++------------------------------------------------ include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 5 ++-- 3 files changed, 7 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/veth.c b/drivers/net/veth.c index de1f13837782..500b9dfccd08 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -729,80 +729,10 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - u32 size, len, max_head_size, off, truesize, page_offset; - struct sk_buff *nskb; - struct page *page; - int i, head_off; - void *va; - - /* We need a private copy of the skb and data buffers since - * the ebpf program can modify it. We segment the original skb - * into order-0 pages without linearize it. - * - * Make sure we have enough space for linear and paged area - */ - max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - - VETH_XDP_HEADROOM); - if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size) - goto drop; - - size = min_t(u32, skb->len, max_head_size); - truesize = SKB_HEAD_ALIGN(size) + VETH_XDP_HEADROOM; - - /* Allocate skb head */ - va = page_pool_dev_alloc_va(rq->page_pool, &truesize); - if (!va) - goto drop; - - nskb = napi_build_skb(va, truesize); - if (!nskb) { - page_pool_free_va(rq->page_pool, va, true); + if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM)) goto drop; - } - - skb_reserve(nskb, VETH_XDP_HEADROOM); - skb_copy_header(nskb, skb); - skb_mark_for_recycle(nskb); - - if (skb_copy_bits(skb, 0, nskb->data, size)) { - consume_skb(nskb); - goto drop; - } - skb_put(nskb, size); - head_off = skb_headroom(nskb) - skb_headroom(skb); - skb_headers_offset_update(nskb, head_off); - - /* Allocate paged area of new skb */ - off = size; - len = skb->len - off; - - for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { - size = min_t(u32, len, PAGE_SIZE); - truesize = size; - - page = page_pool_dev_alloc(rq->page_pool, &page_offset, - &truesize); - if (!page) { - consume_skb(nskb); - goto drop; - } - - skb_add_rx_frag(nskb, i, page, page_offset, size, - truesize); - if (skb_copy_bits(skb, off, - page_address(page) + page_offset, - size)) { - consume_skb(nskb); - goto drop; - } - - len -= size; - off += size; - } - - consume_skb(skb); - skb = nskb; + skb = *pskb; } /* SKB "head" area always have tailroom for skb_shared_info */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index def3d8689c3d..696e7680656f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3446,6 +3446,8 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); bool napi_pp_put_page(struct page *page, bool napi_safe); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bdb94749f05d..0d9a489e6ae1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -895,8 +895,8 @@ static bool is_pp_page(struct page *page) return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } -static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, - unsigned int headroom) +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom) { #if IS_ENABLED(CONFIG_PAGE_POOL) u32 size, truesize, len, max_head_size, off; @@ -975,6 +975,7 @@ static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, return -EOPNOTSUPP; #endif } +EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog) -- cgit v1.2.3 From 4d42b37def70327b2bb19f823d42289aed2cd7c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 13 Feb 2024 06:32:36 +0000 Subject: net: convert dev->reg_state to u8 Prepares things so that dev->reg_state reads can be lockless, by adding WRITE_ONCE() on write side. READ_ONCE()/WRITE_ONCE() do not support bitfields. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 23 ++++++++++++++--------- net/core/dev.c | 8 ++++---- 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3f9c95da51e..631124655107 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1815,6 +1815,15 @@ enum netdev_stat_type { NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ }; +enum netdev_reg_state { + NETREG_UNINITIALIZED = 0, + NETREG_REGISTERED, /* completed register_netdevice */ + NETREG_UNREGISTERING, /* called unregister_netdevice */ + NETREG_UNREGISTERED, /* completed unregister todo */ + NETREG_RELEASED, /* called free_netdev */ + NETREG_DUMMY, /* dummy device for NAPI poll */ +}; + /** * struct net_device - The DEVICE structure. * @@ -2372,13 +2381,7 @@ struct net_device { struct list_head link_watch_list; - enum { NETREG_UNINITIALIZED=0, - NETREG_REGISTERED, /* completed register_netdevice */ - NETREG_UNREGISTERING, /* called unregister_netdevice */ - NETREG_UNREGISTERED, /* completed unregister todo */ - NETREG_RELEASED, /* called free_netdev */ - NETREG_DUMMY, /* dummy device for NAPI poll */ - } reg_state:8; + u8 reg_state; bool dismantle; @@ -5254,7 +5257,9 @@ static inline const char *netdev_name(const struct net_device *dev) static inline const char *netdev_reg_state(const struct net_device *dev) { - switch (dev->reg_state) { + u8 reg_state = READ_ONCE(dev->reg_state); + + switch (reg_state) { case NETREG_UNINITIALIZED: return " (uninitialized)"; case NETREG_REGISTERED: return ""; case NETREG_UNREGISTERING: return " (unregistering)"; @@ -5263,7 +5268,7 @@ static inline const char *netdev_reg_state(const struct net_device *dev) case NETREG_DUMMY: return " (dummy)"; } - WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state); + WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state); return " (unknown)"; } diff --git a/net/core/dev.c b/net/core/dev.c index 720bd6838212..9c95cae9d6ab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10339,7 +10339,7 @@ int register_netdevice(struct net_device *dev) ret = netdev_register_kobject(dev); write_lock(&dev_base_lock); - dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; + WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); write_unlock(&dev_base_lock); if (ret) goto err_uninit_notify; @@ -10630,7 +10630,7 @@ void netdev_run_todo(void) } write_lock(&dev_base_lock); - dev->reg_state = NETREG_UNREGISTERED; + WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); write_unlock(&dev_base_lock); linkwatch_sync_dev(dev); } @@ -11050,7 +11050,7 @@ void free_netdev(struct net_device *dev) } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); - dev->reg_state = NETREG_RELEASED; + WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); @@ -11140,7 +11140,7 @@ void unregister_netdevice_many_notify(struct list_head *head, /* And unlink it from device chain. */ write_lock(&dev_base_lock); unlist_netdevice(dev, false); - dev->reg_state = NETREG_UNREGISTERING; + WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); write_unlock(&dev_base_lock); } flush_all_backlogs(); -- cgit v1.2.3 From 6a2968ee1ee2cc6fce30f6f5724442b34b1483b3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 13 Feb 2024 06:32:42 +0000 Subject: net: add netdev_set_operstate() helper dev_base_lock is going away, add netdev_set_operstate() helper so that hsr does not have to know core internals. Remove dev_base_lock acquisition from rfc2863_policy() v3: use an "unsigned int" for dev->operstate, so that try_cmpxchg() can work on all arches. ( https://lore.kernel.org/oe-kbuild-all/202402081918.OLyGaea3-lkp@intel.com/ ) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/linux/rtnetlink.h | 2 ++ net/core/link_watch.c | 9 ++------- net/core/rtnetlink.c | 22 +++++++++++++++------- net/hsr/hsr_device.c | 22 ++++++---------------- 5 files changed, 26 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 631124655107..697370706a82 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2258,7 +2258,7 @@ struct net_device { const struct tlsdev_ops *tlsdev_ops; #endif - unsigned char operstate; + unsigned int operstate; unsigned char link_mode; unsigned char if_port; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 21780608cf47..cdfc897f1e3c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -172,4 +172,6 @@ rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group) return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group); } +void netdev_set_operstate(struct net_device *dev, int newstate); + #endif /* __LINUX_RTNETLINK_H */ diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 1b93e054c9a3..8ec35194bfcb 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -33,7 +33,7 @@ static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); -static unsigned char default_operstate(const struct net_device *dev) +static unsigned int default_operstate(const struct net_device *dev) { if (netif_testing(dev)) return IF_OPER_TESTING; @@ -62,16 +62,13 @@ static unsigned char default_operstate(const struct net_device *dev) return IF_OPER_UP; } - static void rfc2863_policy(struct net_device *dev) { - unsigned char operstate = default_operstate(dev); + unsigned int operstate = default_operstate(dev); if (operstate == READ_ONCE(dev->operstate)) return; - write_lock(&dev_base_lock); - switch(dev->link_mode) { case IF_LINK_MODE_TESTING: if (operstate == IF_OPER_UP) @@ -88,8 +85,6 @@ static void rfc2863_policy(struct net_device *dev) } WRITE_ONCE(dev->operstate, operstate); - - write_unlock(&dev_base_lock); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 43d92de8601c..e484ba44f23b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -842,9 +842,22 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); +void netdev_set_operstate(struct net_device *dev, int newstate) +{ + unsigned int old = READ_ONCE(dev->operstate); + + do { + if (old == newstate) + return; + } while (!try_cmpxchg(&dev->operstate, &old, newstate)); + + netdev_state_change(dev); +} +EXPORT_SYMBOL(netdev_set_operstate); + static void set_operstate(struct net_device *dev, unsigned char transition) { - unsigned char operstate = dev->operstate; + unsigned char operstate = READ_ONCE(dev->operstate); switch (transition) { case IF_OPER_UP: @@ -866,12 +879,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition) break; } - if (READ_ONCE(dev->operstate) != operstate) { - write_lock(&dev_base_lock); - WRITE_ONCE(dev->operstate, operstate); - write_unlock(&dev_base_lock); - netdev_state_change(dev); - } + netdev_set_operstate(dev, operstate); } static unsigned int rtnl_dev_get_flags(const struct net_device *dev) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index be0e43f46556..5ef6d437db72 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -28,29 +28,19 @@ static bool is_slave_up(struct net_device *dev) return dev && is_admin_up(dev) && netif_oper_up(dev); } -static void __hsr_set_operstate(struct net_device *dev, int transition) -{ - write_lock(&dev_base_lock); - if (READ_ONCE(dev->operstate) != transition) { - WRITE_ONCE(dev->operstate, transition); - write_unlock(&dev_base_lock); - netdev_state_change(dev); - } else { - write_unlock(&dev_base_lock); - } -} - static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { - if (!is_admin_up(master->dev)) { - __hsr_set_operstate(master->dev, IF_OPER_DOWN); + struct net_device *dev = master->dev; + + if (!is_admin_up(dev)) { + netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) - __hsr_set_operstate(master->dev, IF_OPER_UP); + netdev_set_operstate(dev, IF_OPER_UP); else - __hsr_set_operstate(master->dev, IF_OPER_LOWERLAYERDOWN); + netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) -- cgit v1.2.3 From 1b3ef46cb7f2618cc0b507393220a69810f6da12 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 13 Feb 2024 06:32:45 +0000 Subject: net: remove dev_base_lock dev_base_lock is not needed anymore, all remaining users also hold RTNL. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- net/core/dev.c | 39 ++++----------------------------------- 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 697370706a82..c541550b0e6e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3077,8 +3077,6 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev); int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info); -extern rwlock_t dev_base_lock; /* Device list lock */ - #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ diff --git a/net/core/dev.c b/net/core/dev.c index 02cf9fd68da6..d8dd293a7a27 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -168,28 +168,6 @@ static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); -/* - * The @dev_base_head list is protected by @dev_base_lock and the rtnl - * semaphore. - * - * Pure readers hold dev_base_lock for reading, or rcu_read_lock() - * - * Writers must hold the rtnl semaphore while they loop through the - * dev_base_head list, and hold dev_base_lock for writing when they do the - * actual updates. This allows pure readers to access the list even - * while a writer is preparing to update it. - * - * To put it another way, dev_base_lock is held for writing only to - * protect against pure readers; the rtnl semaphore provides the - * protection against other writers. - * - * See, for example usages, register_netdevice() and - * unregister_netdevice(), which must be called with the rtnl - * semaphore held. - */ -DEFINE_RWLOCK(dev_base_lock); -EXPORT_SYMBOL(dev_base_lock); - static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ @@ -395,12 +373,10 @@ static void list_netdevice(struct net_device *dev) ASSERT_RTNL(); - write_lock(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); - write_unlock(&dev_base_lock); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); @@ -427,11 +403,9 @@ static void unlist_netdevice(struct net_device *dev) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ - write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -752,9 +726,9 @@ EXPORT_SYMBOL_GPL(dev_fill_forward_path); * @net: the applicable net namespace * @name: name to find * - * Find an interface by name. Must be called under RTNL semaphore - * or @dev_base_lock. If the name is found a pointer to the device - * is returned. If the name is not found then %NULL is returned. The + * Find an interface by name. Must be called under RTNL semaphore. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ @@ -835,8 +809,7 @@ EXPORT_SYMBOL(netdev_get_by_name); * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful - * about locking. The caller must hold either the RTNL semaphore - * or @dev_base_lock. + * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) @@ -1241,15 +1214,11 @@ rollback: netdev_adjacent_rename_links(dev, oldname); - write_lock(&dev_base_lock); netdev_name_node_del(dev->name_node); - write_unlock(&dev_base_lock); synchronize_net(); - write_lock(&dev_base_lock); netdev_name_node_add(net, dev->name_node); - write_unlock(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); -- cgit v1.2.3 From 81800aef0eba33df2b30f2e29a0137078b9ba256 Mon Sep 17 00:00:00 2001 From: "Ricardo B. Marliere" Date: Tue, 13 Feb 2024 11:48:00 -0300 Subject: net: mdio_bus: make mdio_bus_type const Since commit d492cc2573a0 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the mdio_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Ricardo B. Marliere Reviewed-by: Andrew Lunn Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240213-bus_cleanup-mdio-v1-1-f9e799da7fda@marliere.net Signed-off-by: Paolo Abeni --- drivers/net/phy/mdio_bus.c | 2 +- drivers/net/phy/phy_device.c | 3 +-- include/linux/phy.h | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 08624f073014..b765466e767f 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -1426,7 +1426,7 @@ static const struct attribute_group *mdio_bus_dev_groups[] = { NULL, }; -struct bus_type mdio_bus_type = { +const struct bus_type mdio_bus_type = { .name = "mdio_bus", .dev_groups = mdio_bus_dev_groups, .match = mdio_bus_match, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9f37c0bfbf8d..d63dca535746 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1604,7 +1604,6 @@ EXPORT_SYMBOL(phy_attach_direct); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface) { - struct bus_type *bus = &mdio_bus_type; struct phy_device *phydev; struct device *d; int rc; @@ -1615,7 +1614,7 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, /* Search the list of PHY devices on the mdio bus for the * PHY with the requested name */ - d = bus_find_device_by_name(bus, NULL, bus_id); + d = bus_find_device_by_name(&mdio_bus_type, NULL, bus_id); if (!d) { pr_err("PHY %s not found\n", bus_id); return ERR_PTR(-ENODEV); diff --git a/include/linux/phy.h b/include/linux/phy.h index 2249cdb5957a..c2dda21b39e1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -2129,7 +2129,7 @@ static inline bool phy_package_probe_once(struct phy_device *phydev) return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } -extern struct bus_type mdio_bus_type; +extern const struct bus_type mdio_bus_type; struct mdio_board_info { const char *bus_id; -- cgit v1.2.3 From a5fcea2d2f790aa90b6e996d411ae2cf8db55186 Mon Sep 17 00:00:00 2001 From: Alex Henrie Date: Tue, 13 Feb 2024 23:26:31 -0700 Subject: net: ipv6/addrconf: introduce a regen_min_advance sysctl In RFC 8981, REGEN_ADVANCE cannot be less than 2 seconds, and the RFC does not permit the creation of temporary addresses with lifetimes shorter than that: > When processing a Router Advertisement with a > Prefix Information option carrying a prefix for the purposes of > address autoconfiguration (i.e., the A bit is set), the host MUST > perform the following steps: > 5. A temporary address is created only if this calculated preferred > lifetime is greater than REGEN_ADVANCE time units. However, some users want to change their IPv6 address as frequently as possible regardless of the RFC's arbitrary minimum lifetime. For the benefit of those users, add a regen_min_advance sysctl parameter that can be set to below or above 2 seconds. Link: https://datatracker.ietf.org/doc/html/rfc8981 Signed-off-by: Alex Henrie Reviewed-by: David Ahern Signed-off-by: Paolo Abeni --- Documentation/networking/ip-sysctl.rst | 10 ++++++++++ include/linux/ipv6.h | 1 + include/net/addrconf.h | 5 +++-- net/ipv6/addrconf.c | 11 ++++++++++- 4 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 458305931345..407d917d1a36 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2535,6 +2535,16 @@ max_desync_factor - INTEGER Default: 600 +regen_min_advance - INTEGER + How far in advance (in seconds), at minimum, to create a new temporary + address before the current one is deprecated. This value is added to + the amount of time that may be required for duplicate address detection + to determine when to create a new address. Linux permits setting this + value to less than the default of 2 seconds, but a value less than 2 + does not conform to RFC 8981. + + Default: 2 + regen_max_retry - INTEGER Number of attempts before give up attempting to generate valid temporary addresses. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5e605e384aac..ef3aa060a289 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -27,6 +27,7 @@ struct ipv6_devconf { __s32 use_tempaddr; __s32 temp_valid_lft; __s32 temp_prefered_lft; + __s32 regen_min_advance; __s32 regen_max_retry; __s32 max_desync_factor; __s32 max_addresses; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 61ebe723ee4d..30d6f1e84e46 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -8,8 +8,9 @@ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ -#define TEMP_VALID_LIFETIME (7*86400) -#define TEMP_PREFERRED_LIFETIME (86400) +#define TEMP_VALID_LIFETIME (7*86400) /* 1 week */ +#define TEMP_PREFERRED_LIFETIME (86400) /* 24 hours */ +#define REGEN_MIN_ADVANCE (2) /* 2 seconds */ #define REGEN_MAX_RETRY (3) #define MAX_DESYNC_FACTOR (600) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 65e886d7d80c..283823fba96a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -1341,7 +1343,7 @@ out: static unsigned long ipv6_get_regen_advance(struct inet6_dev *idev) { - return 2 + idev->cnf.regen_max_retry * + return idev->cnf.regen_min_advance + idev->cnf.regen_max_retry * idev->cnf.dad_transmits * max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; } @@ -6819,6 +6821,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "regen_min_advance", + .data = &ipv6_devconf.regen_min_advance, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, -- cgit v1.2.3 From 80e4021c25d8c1ddae0dd655ed5f6b1e938dd79b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 14 Feb 2024 21:16:19 +0100 Subject: net: mdio: add helpers for accessing the EEE CAP2 registers This adds helpers for accessing the EEE CAP2 registers. For now only 2500baseT and 5000baseT modes are supported. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/mdio.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 79ceee3c8673..fd8ff310f9eb 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -439,6 +439,42 @@ static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val) adv, val & MDIO_EEE_10GKR); } +/** + * mii_eee_cap2_mod_linkmode_sup_t() + * @adv: target the linkmode settings + * @val: register value + * + * A function that translates value of following registers to the linkmode: + * IEEE 802.3-2022 45.2.3.11 "EEE control and capability 2" register (3.21) + */ +static inline void mii_eee_cap2_mod_linkmode_sup_t(unsigned long *adv, u32 val) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + adv, val & MDIO_EEE_2_5GT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + adv, val & MDIO_EEE_5GT); +} + +/** + * mii_eee_cap2_mod_linkmode_adv_t() + * @adv: target the linkmode advertisement settings + * @val: register value + * + * A function that translates value of following registers to the linkmode: + * IEEE 802.3-2022 45.2.7.16 "EEE advertisement 2" register (7.62) + * IEEE 802.3-2022 45.2.7.17 "EEE link partner ability 2" register (7.63) + * Note: Currently this function is the same as mii_eee_cap2_mod_linkmode_sup_t. + * For certain, not yet supported, modes however the bits differ. + * Therefore create separate functions already. + */ +static inline void mii_eee_cap2_mod_linkmode_adv_t(unsigned long *adv, u32 val) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + adv, val & MDIO_EEE_2_5GT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + adv, val & MDIO_EEE_5GT); +} + /** * linkmode_to_mii_eee_cap1_t() * @adv: the linkmode advertisement settings @@ -466,6 +502,25 @@ static inline u32 linkmode_to_mii_eee_cap1_t(unsigned long *adv) return result; } +/** + * linkmode_to_mii_eee_cap2_t() + * @adv: the linkmode advertisement settings + * + * A function that translates linkmode to value for IEEE 802.3-2022 45.2.7.16 + * "EEE advertisement 2" register (7.62) + */ +static inline u32 linkmode_to_mii_eee_cap2_t(unsigned long *adv) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, adv)) + result |= MDIO_EEE_2_5GT; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, adv)) + result |= MDIO_EEE_5GT; + + return result; +} + /** * mii_10base_t1_adv_mod_linkmode_t() * @adv: linkmode advertisement settings -- cgit v1.2.3 From ef6ee3a31bdc699391f2db4eff407fdb06895809 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 14 Feb 2024 21:17:11 +0100 Subject: net: phy: add PHY_EEE_CAP2_FEATURES As a prerequisite for adding EEE CAP2 register support, complement PHY_EEE_CAP1_FEATURES with PHY_EEE_CAP2_FEATURES. For now only 2500baseT and 5000baseT modes are supported. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 11 +++++++++++ include/linux/phy.h | 2 ++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d63dca535746..2eefee970851 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -148,6 +148,14 @@ static const int phy_eee_cap1_features_array[] = { __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_eee_cap1_features); +static const int phy_eee_cap2_features_array[] = { + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + ETHTOOL_LINK_MODE_5000baseT_Full_BIT, +}; + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_eee_cap2_features); + static void features_init(void) { /* 10/100 half/full*/ @@ -232,6 +240,9 @@ static void features_init(void) linkmode_set_bit_array(phy_eee_cap1_features_array, ARRAY_SIZE(phy_eee_cap1_features_array), phy_eee_cap1_features); + linkmode_set_bit_array(phy_eee_cap2_features_array, + ARRAY_SIZE(phy_eee_cap2_features_array), + phy_eee_cap2_features); } diff --git a/include/linux/phy.h b/include/linux/phy.h index c2dda21b39e1..e3ab2c347a59 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -54,6 +54,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) @@ -65,6 +66,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; #define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) +#define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; -- cgit v1.2.3 From 21d2e6737c9789aa9b23c8a4131cbca8260139fd Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Wed, 14 Feb 2024 14:34:03 -0800 Subject: net: add netmem to skb_frag_t Use struct netmem* instead of page in skb_frag_t. Currently struct netmem* is always a struct page underneath, but the abstraction allows efforts to add support for skb frags not backed by pages. There is unfortunately 1 instance where the skb_frag_t is assumed to be a exactly a bio_vec in kcm. For this case, WARN_ON_ONCE and return error before doing a cast. Add skb[_frag]_fill_netmem_*() and skb_add_rx_frag_netmem() helpers so that the API can be used to create netmem skbs. Signed-off-by: Mina Almasry Acked-by: Paolo Abeni Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 100 +++++++++++++++++++++++++++++++++++-------------- net/core/skbuff.c | 34 +++++++++++++---- net/kcm/kcmsock.c | 7 ++-- 3 files changed, 102 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 696e7680656f..e3a2ed5d09ad 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #endif #include #include +#include /** * DOC: skb checksums @@ -359,7 +360,11 @@ extern int sysctl_max_skb_frags; */ #define GSO_BY_FRAGS 0xFFFF -typedef struct bio_vec skb_frag_t; +typedef struct skb_frag { + netmem_ref netmem; + unsigned int len; + unsigned int offset; +} skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment @@ -367,7 +372,7 @@ typedef struct bio_vec skb_frag_t; */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { - return frag->bv_len; + return frag->len; } /** @@ -377,7 +382,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag) */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { - frag->bv_len = size; + frag->len = size; } /** @@ -387,7 +392,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { - frag->bv_len += delta; + frag->len += delta; } /** @@ -397,7 +402,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { - frag->bv_len -= delta; + frag->len -= delta; } /** @@ -417,7 +422,7 @@ static inline bool skb_frag_must_loop(struct page *p) * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on - * @f_off: offset from start of f->bv_page + * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, @@ -2429,22 +2434,37 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, + netmem_ref netmem, int off, + int size) +{ + frag->netmem = netmem; + frag->offset = off; + skb_frag_size_set(frag, size); +} + static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); + skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); +} + +static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, + int i, netmem_ref netmem, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &shinfo->frags[i]; - - skb_frag_fill_page_desc(frag, page, off, size); + __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, + size); } /** @@ -2460,10 +2480,10 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) } /** - * __skb_fill_page_desc - initialise a paged fragment in an skb + * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised - * @i: paged fragment index to initialise - * @page: the page to use for this fragment + * @i: fragment index to initialise + * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * @@ -2472,10 +2492,12 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) * * Does not take any additional reference on the fragment. */ -static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, - struct page *page, int off, int size) +static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, + netmem_ref netmem, int off, int size) { - __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); + struct page *page = netmem_to_page(netmem); + + __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely @@ -2483,7 +2505,20 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, */ page = compound_head(page); if (page_is_pfmemalloc(page)) - skb->pfmemalloc = true; + skb->pfmemalloc = true; +} + +static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, + struct page *page, int off, int size) +{ + __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); +} + +static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, + netmem_ref netmem, int off, int size) +{ + __skb_fill_netmem_desc(skb, i, netmem, off, size); + skb_shinfo(skb)->nr_frags = i + 1; } /** @@ -2503,8 +2538,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - __skb_fill_page_desc(skb, i, page, off, size); - skb_shinfo(skb)->nr_frags = i + 1; + skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** @@ -2528,8 +2562,16 @@ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, shinfo->nr_frags = i + 1; } -void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, - int size, unsigned int truesize); +void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, + int off, int size, unsigned int truesize); + +static inline void skb_add_rx_frag(struct sk_buff *skb, int i, + struct page *page, int off, int size, + unsigned int truesize) +{ + skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, + truesize); +} void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); @@ -3378,7 +3420,7 @@ static inline void skb_propagate_pfmemalloc(const struct page *page, */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { - return frag->bv_offset; + return frag->offset; } /** @@ -3388,7 +3430,7 @@ static inline unsigned int skb_frag_off(const skb_frag_t *frag) */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { - frag->bv_offset += delta; + frag->offset += delta; } /** @@ -3398,7 +3440,7 @@ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { - frag->bv_offset = offset; + frag->offset = offset; } /** @@ -3409,7 +3451,7 @@ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { - fragto->bv_offset = fragfrom->bv_offset; + fragto->offset = fragfrom->offset; } /** @@ -3420,7 +3462,7 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { - return frag->bv_page; + return netmem_to_page(frag->netmem); } /** @@ -3528,7 +3570,7 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { - fragto->bv_page = fragfrom->bv_page; + fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b41856585c24..1434c422f76e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -115,6 +115,24 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init; int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); +/* kcm_write_msgs() relies on casting paged frags to bio_vec to use + * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the + * netmem is a page. + */ +static_assert(offsetof(struct bio_vec, bv_page) == + offsetof(skb_frag_t, netmem)); +static_assert(sizeof_field(struct bio_vec, bv_page) == + sizeof_field(skb_frag_t, netmem)); + +static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len)); +static_assert(sizeof_field(struct bio_vec, bv_len) == + sizeof_field(skb_frag_t, len)); + +static_assert(offsetof(struct bio_vec, bv_offset) == + offsetof(skb_frag_t, offset)); +static_assert(sizeof_field(struct bio_vec, bv_offset) == + sizeof_field(skb_frag_t, offset)); + #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, static const char * const drop_reasons[] = { @@ -845,17 +863,17 @@ skb_fail: } EXPORT_SYMBOL(__napi_alloc_skb); -void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, - int size, unsigned int truesize) +void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, + int off, int size, unsigned int truesize) { DEBUG_NET_WARN_ON_ONCE(size > truesize); - skb_fill_page_desc(skb, i, page, off, size); + skb_fill_netmem_desc(skb, i, netmem, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } -EXPORT_SYMBOL(skb_add_rx_frag); +EXPORT_SYMBOL(skb_add_rx_frag_netmem); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) @@ -1999,10 +2017,11 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { - __skb_fill_page_desc(skb, i, head, 0, psize); + __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize); head = (struct page *)page_private(head); } - __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); + __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0, + d_off); skb_shinfo(skb)->nr_frags = new_frags; release: @@ -3740,7 +3759,8 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); - __skb_fill_page_desc(to, 0, page, offset, plen); + __skb_fill_netmem_desc(to, 0, page_to_netmem(page), + offset, plen); get_page(page); j = 1; len -= plen; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 1184d40167b8..73c200c5c8e4 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -627,7 +627,8 @@ retry: skb = txm->frag_skb; } - if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { + if (WARN_ON(!skb_shinfo(skb)->nr_frags) || + WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) { ret = -EINVAL; goto out; } @@ -637,8 +638,8 @@ retry: msize += skb_frag_size(&skb_shinfo(skb)->frags[i]); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, - skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags, - msize); + (const struct bio_vec *)skb_shinfo(skb)->frags, + skb_shinfo(skb)->nr_frags, msize); iov_iter_advance(&msg.msg_iter, txm->frag_offset); do { -- cgit v1.2.3 From 219eee9c0d16f1b754a8b85275854ab17df0850a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 16 Feb 2024 12:36:57 +0100 Subject: net: skbuff: add overflow debug check to pull/push helpers syzbot managed to trigger following splat: BUG: KASAN: use-after-free in __skb_flow_dissect+0x4a3b/0x5e50 Read of size 1 at addr ffff888208a4000e by task a.out/2313 [..] __skb_flow_dissect+0x4a3b/0x5e50 __skb_get_hash+0xb4/0x400 ip_tunnel_xmit+0x77e/0x26f0 ipip_tunnel_xmit+0x298/0x410 .. Analysis shows that the skb has a valid ->head, but bogus ->data pointer. skb->data gets its bogus value via the neigh layer, which does: 1556 __skb_pull(skb, skb_network_offset(skb)); ... and the skb was already dodgy at this point: skb_network_offset(skb) returns a negative value due to an earlier overflow of skb->network_header (u16). __skb_pull thus "adjusts" skb->data by a huge offset, pointing outside skb->head area. Allow debug builds to splat when we try to pull/push more than INT_MAX bytes. After this, the syzkaller reproducer yields a more precise splat before the flow dissector attempts to read off skb->data memory: WARNING: CPU: 5 PID: 2313 at include/linux/skbuff.h:2653 neigh_connected_output+0x28e/0x400 ip_finish_output2+0xb25/0xed0 iptunnel_xmit+0x4ff/0x870 ipgre_xmit+0x78e/0xbb0 Signed-off-by: Florian Westphal Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240216113700.23013-1-fw@strlen.de Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e3a2ed5d09ad..28c7cb7ce251 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2684,6 +2684,8 @@ static inline void skb_put_u8(struct sk_buff *skb, u8 val) void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->data -= len; skb->len += len; return skb->data; @@ -2692,6 +2694,8 @@ static inline void *__skb_push(struct sk_buff *skb, unsigned int len) void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) @@ -2716,6 +2720,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; -- cgit v1.2.3 From 2f3bfa8e30b5b4864a200be0dc2fb55d8e4b35e4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 17 Feb 2024 11:03:06 +0100 Subject: net: wan: framer: constify of_phandle_args in xlate The xlate callbacks are supposed to translate of_phandle_args to proper provider without modifying the of_phandle_args. Make the argument pointer to const for code safety and readability. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240217100306.86740-1-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/wan/framer/framer-core.c | 9 +++++---- include/linux/framer/framer-provider.h | 14 +++++++------- 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wan/framer/framer-core.c b/drivers/net/wan/framer/framer-core.c index c04dc88bda6c..33b358b99f70 100644 --- a/drivers/net/wan/framer/framer-core.c +++ b/drivers/net/wan/framer/framer-core.c @@ -384,7 +384,7 @@ static struct framer_provider *framer_provider_of_lookup(const struct device_nod return ERR_PTR(-EPROBE_DEFER); } -static struct framer *framer_of_get_from_provider(struct of_phandle_args *args) +static struct framer *framer_of_get_from_provider(const struct of_phandle_args *args) { struct framer_provider *framer_provider; struct framer *framer; @@ -735,7 +735,8 @@ EXPORT_SYMBOL_GPL(devm_framer_create); * should provide a custom of_xlate function that reads the *args* and returns * the appropriate framer. */ -struct framer *framer_provider_simple_of_xlate(struct device *dev, struct of_phandle_args *args) +struct framer *framer_provider_simple_of_xlate(struct device *dev, + const struct of_phandle_args *args) { struct class_dev_iter iter; struct framer *framer; @@ -768,7 +769,7 @@ EXPORT_SYMBOL_GPL(framer_provider_simple_of_xlate); struct framer_provider * __framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { struct framer_provider *framer_provider; @@ -830,7 +831,7 @@ static void devm_framer_provider_of_unregister(struct device *dev, void *res) struct framer_provider * __devm_framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { struct framer_provider **ptr, *framer_provider; diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h index 782cd5fc83d5..f6fd2dd92591 100644 --- a/include/linux/framer/framer-provider.h +++ b/include/linux/framer/framer-provider.h @@ -93,7 +93,7 @@ struct framer_provider { struct module *owner; struct list_head list; struct framer * (*of_xlate)(struct device *dev, - struct of_phandle_args *args); + const struct of_phandle_args *args); }; static inline void framer_set_drvdata(struct framer *framer, void *data) @@ -118,19 +118,19 @@ struct framer *devm_framer_create(struct device *dev, struct device_node *node, const struct framer_ops *ops); struct framer *framer_provider_simple_of_xlate(struct device *dev, - struct of_phandle_args *args); + const struct of_phandle_args *args); struct framer_provider * __framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)); + const struct of_phandle_args *args)); void framer_provider_of_unregister(struct framer_provider *framer_provider); struct framer_provider * __devm_framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)); + const struct of_phandle_args *args)); void framer_notify_status_change(struct framer *framer); @@ -154,7 +154,7 @@ static inline struct framer *devm_framer_create(struct device *dev, struct devic } static inline struct framer *framer_provider_simple_of_xlate(struct device *dev, - struct of_phandle_args *args) + const struct of_phandle_args *args) { return ERR_PTR(-ENOSYS); } @@ -162,7 +162,7 @@ static inline struct framer *framer_provider_simple_of_xlate(struct device *dev, static inline struct framer_provider * __framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { return ERR_PTR(-ENOSYS); } @@ -174,7 +174,7 @@ void framer_provider_of_unregister(struct framer_provider *framer_provider) static inline struct framer_provider * __devm_framer_provider_of_register(struct device *dev, struct module *owner, struct framer *(*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 3f801968889459ecae1eab524b039676e6eaa319 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 14 Feb 2024 14:41:02 +0100 Subject: netfilter: move nf_reinject into nfnetlink_queue modules No need to keep this in the core, move it to the nfnetlink_queue module. nf_reroute is moved too, there were no other callers. Signed-off-by: Florian Westphal --- include/linux/netfilter.h | 1 - include/net/netfilter/nf_queue.h | 1 - net/netfilter/nf_queue.c | 106 ----------------------------- net/netfilter/nfnetlink_queue.c | 142 +++++++++++++++++++++++++++++++++++++++ net/netfilter/utils.c | 37 ---------- 5 files changed, 142 insertions(+), 145 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 80900d910992..ffb5e0297eb5 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -370,7 +370,6 @@ __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, u_int8_t protocol, unsigned short family); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family); -int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry); #include diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index c81021ab07aa..4aeffddb7586 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -35,7 +35,6 @@ struct nf_queue_handler { void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); -void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_free(struct nf_queue_entry *entry); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index e2f334f70281..7f12e56e6e52 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -248,109 +248,3 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, return 0; } EXPORT_SYMBOL_GPL(nf_queue); - -static unsigned int nf_iterate(struct sk_buff *skb, - struct nf_hook_state *state, - const struct nf_hook_entries *hooks, - unsigned int *index) -{ - const struct nf_hook_entry *hook; - unsigned int verdict, i = *index; - - while (i < hooks->num_hook_entries) { - hook = &hooks->hooks[i]; -repeat: - verdict = nf_hook_entry_hookfn(hook, skb, state); - if (verdict != NF_ACCEPT) { - *index = i; - if (verdict != NF_REPEAT) - return verdict; - goto repeat; - } - i++; - } - - *index = i; - return NF_ACCEPT; -} - -static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) -{ - switch (pf) { -#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE - case NFPROTO_BRIDGE: - return rcu_dereference(net->nf.hooks_bridge[hooknum]); -#endif - case NFPROTO_IPV4: - return rcu_dereference(net->nf.hooks_ipv4[hooknum]); - case NFPROTO_IPV6: - return rcu_dereference(net->nf.hooks_ipv6[hooknum]); - default: - WARN_ON_ONCE(1); - return NULL; - } - - return NULL; -} - -/* Caller must hold rcu read-side lock */ -void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) -{ - const struct nf_hook_entry *hook_entry; - const struct nf_hook_entries *hooks; - struct sk_buff *skb = entry->skb; - const struct net *net; - unsigned int i; - int err; - u8 pf; - - net = entry->state.net; - pf = entry->state.pf; - - hooks = nf_hook_entries_head(net, pf, entry->state.hook); - - i = entry->hook_index; - if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { - kfree_skb(skb); - nf_queue_entry_free(entry); - return; - } - - hook_entry = &hooks->hooks[i]; - - /* Continue traversal iff userspace said ok... */ - if (verdict == NF_REPEAT) - verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); - - if (verdict == NF_ACCEPT) { - if (nf_reroute(skb, entry) < 0) - verdict = NF_DROP; - } - - if (verdict == NF_ACCEPT) { -next_hook: - ++i; - verdict = nf_iterate(skb, &entry->state, hooks, &i); - } - - switch (verdict & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_STOP: - local_bh_disable(); - entry->state.okfn(entry->state.net, entry->state.sk, skb); - local_bh_enable(); - break; - case NF_QUEUE: - err = nf_queue(skb, &entry->state, i, verdict); - if (err == 1) - goto next_hook; - break; - case NF_STOLEN: - break; - default: - kfree_skb(skb); - } - - nf_queue_entry_free(entry); -} -EXPORT_SYMBOL(nf_reinject); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5cf38fc0a366..00f4bd21c59b 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -225,6 +225,148 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) return entry; } +static unsigned int nf_iterate(struct sk_buff *skb, + struct nf_hook_state *state, + const struct nf_hook_entries *hooks, + unsigned int *index) +{ + const struct nf_hook_entry *hook; + unsigned int verdict, i = *index; + + while (i < hooks->num_hook_entries) { + hook = &hooks->hooks[i]; +repeat: + verdict = nf_hook_entry_hookfn(hook, skb, state); + if (verdict != NF_ACCEPT) { + *index = i; + if (verdict != NF_REPEAT) + return verdict; + goto repeat; + } + i++; + } + + *index = i; + return NF_ACCEPT; +} + +static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) +{ + switch (pf) { +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + case NFPROTO_BRIDGE: + return rcu_dereference(net->nf.hooks_bridge[hooknum]); +#endif + case NFPROTO_IPV4: + return rcu_dereference(net->nf.hooks_ipv4[hooknum]); + case NFPROTO_IPV6: + return rcu_dereference(net->nf.hooks_ipv6[hooknum]); + default: + WARN_ON_ONCE(1); + return NULL; + } + + return NULL; +} + +static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) +{ +#ifdef CONFIG_INET + const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); + + if (entry->state.hook == NF_INET_LOCAL_OUT) { + const struct iphdr *iph = ip_hdr(skb); + + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); + } +#endif + return 0; +} + +static int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) +{ + const struct nf_ipv6_ops *v6ops; + int ret = 0; + + switch (entry->state.pf) { + case AF_INET: + ret = nf_ip_reroute(skb, entry); + break; + case AF_INET6: + v6ops = rcu_dereference(nf_ipv6_ops); + if (v6ops) + ret = v6ops->reroute(skb, entry); + break; + } + return ret; +} + +/* caller must hold rcu read-side lock */ +static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) +{ + const struct nf_hook_entry *hook_entry; + const struct nf_hook_entries *hooks; + struct sk_buff *skb = entry->skb; + const struct net *net; + unsigned int i; + int err; + u8 pf; + + net = entry->state.net; + pf = entry->state.pf; + + hooks = nf_hook_entries_head(net, pf, entry->state.hook); + + i = entry->hook_index; + if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { + kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); + nf_queue_entry_free(entry); + return; + } + + hook_entry = &hooks->hooks[i]; + + /* Continue traversal iff userspace said ok... */ + if (verdict == NF_REPEAT) + verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); + + if (verdict == NF_ACCEPT) { + if (nf_reroute(skb, entry) < 0) + verdict = NF_DROP; + } + + if (verdict == NF_ACCEPT) { +next_hook: + ++i; + verdict = nf_iterate(skb, &entry->state, hooks, &i); + } + + switch (verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + case NF_STOP: + local_bh_disable(); + entry->state.okfn(entry->state.net, entry->state.sk, skb); + local_bh_enable(); + break; + case NF_QUEUE: + err = nf_queue(skb, &entry->state, i, verdict); + if (err == 1) + goto next_hook; + break; + case NF_STOLEN: + break; + default: + kfree_skb(skb); + } + + nf_queue_entry_free(entry); +} + static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index acef4155f0da..008419db815a 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -179,43 +179,6 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, } EXPORT_SYMBOL_GPL(nf_route); -static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) -{ -#ifdef CONFIG_INET - const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - - if (entry->state.hook == NF_INET_LOCAL_OUT) { - const struct iphdr *iph = ip_hdr(skb); - - if (!(iph->tos == rt_info->tos && - skb->mark == rt_info->mark && - iph->daddr == rt_info->daddr && - iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, entry->state.sk, - skb, RTN_UNSPEC); - } -#endif - return 0; -} - -int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) -{ - const struct nf_ipv6_ops *v6ops; - int ret = 0; - - switch (entry->state.pf) { - case AF_INET: - ret = nf_ip_reroute(skb, entry); - break; - case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - ret = v6ops->reroute(skb, entry); - break; - } - return ret; -} - /* Only get and check the lengths, not do any hop-by-hop stuff. */ int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen) { -- cgit v1.2.3 From 78b88ef392c1ccc189c74cf73c179cf59d23a258 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 19 Feb 2024 17:45:48 +0000 Subject: net: wan: framer: remove children from struct framer_ops kdoc Remove documentation of non-existent children field from the Kernel doc for struct framer_ops. Introduced by 82c944d05b1a ("net: wan: Add framer framework support") Signed-off-by: Simon Horman Acked-by: Herve Codina Signed-off-by: David S. Miller --- include/linux/framer/framer-provider.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h index f6fd2dd92591..9724d4b44b9c 100644 --- a/include/linux/framer/framer-provider.h +++ b/include/linux/framer/framer-provider.h @@ -83,7 +83,6 @@ struct framer_ops { /** * struct framer_provider - represents the framer provider * @dev: framer provider device - * @children: can be used to override the default (dev->of_node) child node * @owner: the module owner having of_xlate * @list: to maintain a linked list of framer providers * @of_xlate: function pointer to obtain framer instance from framer pointer -- cgit v1.2.3 From ee975351cf0c2a11cdf97eae58265c126cb32850 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 19 Feb 2024 12:40:51 -0800 Subject: net: mdio: mdio-bcm-unimac: Manage clock around I/O accesses Up until now we have managed not to have the mdio-bcm-unimac manage its clock except during probe and suspend/resume. This works most of the time, except where it does not. With a fully modular build, we can get into a situation whereby the GENET driver is fully registered, and so is the mdio-bcm-unimac driver, however the Ethernet PHY driver is not yet, because it depends on a resource that is not yet available (e.g.: GPIO provider). In that state, the network device is not usable yet, and so to conserve power, the GENET driver will have turned off its "main" clock which feeds its MDIO controller. When the PHY driver finally probes however, we make an access to the PHY registers to e.g.: disable interrupts, and this causes a bus error within the MDIO controller space because the MDIO controller clock(s) are turned off. To remedy that, we manage the clock around all of the I/O accesses to the hardware which are done exclusively during read, write and clock divider configuration. This ensures that the register space is accessible, and this also ensures that there are not unnecessarily elevated reference counts keeping the clocks active when the network device is administratively turned off. It would be the case with the previous way of managing the clock. Reviewed-by: Jacob Keller Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/mdio/mdio-bcm-unimac.c | 93 ++++++++++++++------------- include/linux/platform_data/mdio-bcm-unimac.h | 3 + 2 files changed, 53 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c index 68f8ee0ec8ba..6fe08427fdd4 100644 --- a/drivers/net/mdio/mdio-bcm-unimac.c +++ b/drivers/net/mdio/mdio-bcm-unimac.c @@ -94,6 +94,10 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg) int ret; u32 cmd; + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + /* Prepare the read operation */ cmd = MDIO_RD | (phy_id << MDIO_PMD_SHIFT) | (reg << MDIO_REG_SHIFT); unimac_mdio_writel(priv, cmd, MDIO_CMD); @@ -103,7 +107,7 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg) ret = priv->wait_func(priv->wait_func_data); if (ret) - return ret; + goto out; cmd = unimac_mdio_readl(priv, MDIO_CMD); @@ -112,10 +116,15 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg) * that condition here and ignore the MDIO controller read failure * indication. */ - if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (cmd & MDIO_READ_FAIL)) - return -EIO; + if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (cmd & MDIO_READ_FAIL)) { + ret = -EIO; + goto out; + } - return cmd & 0xffff; + ret = cmd & 0xffff; +out: + clk_disable_unprepare(priv->clk); + return ret; } static int unimac_mdio_write(struct mii_bus *bus, int phy_id, @@ -123,6 +132,11 @@ static int unimac_mdio_write(struct mii_bus *bus, int phy_id, { struct unimac_mdio_priv *priv = bus->priv; u32 cmd; + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; /* Prepare the write operation */ cmd = MDIO_WR | (phy_id << MDIO_PMD_SHIFT) | @@ -131,7 +145,10 @@ static int unimac_mdio_write(struct mii_bus *bus, int phy_id, unimac_mdio_start(priv); - return priv->wait_func(priv->wait_func_data); + ret = priv->wait_func(priv->wait_func_data); + clk_disable_unprepare(priv->clk); + + return ret; } /* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with @@ -178,14 +195,19 @@ static int unimac_mdio_reset(struct mii_bus *bus) return 0; } -static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv) +static int unimac_mdio_clk_set(struct unimac_mdio_priv *priv) { unsigned long rate; u32 reg, div; + int ret; /* Keep the hardware default values */ if (!priv->clk_freq) - return; + return 0; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; if (!priv->clk) rate = 250000000; @@ -195,7 +217,8 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv) div = (rate / (2 * priv->clk_freq)) - 1; if (div & ~MDIO_CLK_DIV_MASK) { pr_warn("Incorrect MDIO clock frequency, ignoring\n"); - return; + ret = 0; + goto out; } /* The MDIO clock is the reference clock (typically 250Mhz) divided by @@ -205,6 +228,9 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv) reg &= ~(MDIO_CLK_DIV_MASK << MDIO_CLK_DIV_SHIFT); reg |= div << MDIO_CLK_DIV_SHIFT; unimac_mdio_writel(priv, reg, MDIO_CFG); +out: + clk_disable_unprepare(priv->clk); + return ret; } static int unimac_mdio_probe(struct platform_device *pdev) @@ -235,24 +261,12 @@ static int unimac_mdio_probe(struct platform_device *pdev) return -ENOMEM; } - priv->clk = devm_clk_get_optional(&pdev->dev, NULL); - if (IS_ERR(priv->clk)) - return PTR_ERR(priv->clk); - - ret = clk_prepare_enable(priv->clk); - if (ret) - return ret; - if (of_property_read_u32(np, "clock-frequency", &priv->clk_freq)) priv->clk_freq = 0; - unimac_mdio_clk_set(priv); - priv->mii_bus = mdiobus_alloc(); - if (!priv->mii_bus) { - ret = -ENOMEM; - goto out_clk_disable; - } + if (!priv->mii_bus) + return -ENOMEM; bus = priv->mii_bus; bus->priv = priv; @@ -261,17 +275,29 @@ static int unimac_mdio_probe(struct platform_device *pdev) priv->wait_func = pdata->wait_func; priv->wait_func_data = pdata->wait_func_data; bus->phy_mask = ~pdata->phy_mask; + priv->clk = pdata->clk; } else { bus->name = "unimac MII bus"; priv->wait_func_data = priv; priv->wait_func = unimac_mdio_poll; + priv->clk = devm_clk_get_optional(&pdev->dev, NULL); + } + + if (IS_ERR(priv->clk)) { + ret = PTR_ERR(priv->clk); + goto out_mdio_free; } + bus->parent = &pdev->dev; bus->read = unimac_mdio_read; bus->write = unimac_mdio_write; bus->reset = unimac_mdio_reset; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id); + ret = unimac_mdio_clk_set(priv); + if (ret) + goto out_mdio_free; + ret = of_mdiobus_register(bus, np); if (ret) { dev_err(&pdev->dev, "MDIO bus registration failed\n"); @@ -286,8 +312,6 @@ static int unimac_mdio_probe(struct platform_device *pdev) out_mdio_free: mdiobus_free(bus); -out_clk_disable: - clk_disable_unprepare(priv->clk); return ret; } @@ -297,34 +321,17 @@ static void unimac_mdio_remove(struct platform_device *pdev) mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); - clk_disable_unprepare(priv->clk); -} - -static int __maybe_unused unimac_mdio_suspend(struct device *d) -{ - struct unimac_mdio_priv *priv = dev_get_drvdata(d); - - clk_disable_unprepare(priv->clk); - - return 0; } static int __maybe_unused unimac_mdio_resume(struct device *d) { struct unimac_mdio_priv *priv = dev_get_drvdata(d); - int ret; - ret = clk_prepare_enable(priv->clk); - if (ret) - return ret; - - unimac_mdio_clk_set(priv); - - return 0; + return unimac_mdio_clk_set(priv); } static SIMPLE_DEV_PM_OPS(unimac_mdio_pm_ops, - unimac_mdio_suspend, unimac_mdio_resume); + NULL, unimac_mdio_resume); static const struct of_device_id unimac_mdio_ids[] = { { .compatible = "brcm,asp-v2.1-mdio", }, diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h index 8a5f9f0b2c52..724e1f57b81f 100644 --- a/include/linux/platform_data/mdio-bcm-unimac.h +++ b/include/linux/platform_data/mdio-bcm-unimac.h @@ -1,11 +1,14 @@ #ifndef __MDIO_BCM_UNIMAC_PDATA_H #define __MDIO_BCM_UNIMAC_PDATA_H +struct clk; + struct unimac_mdio_pdata { u32 phy_mask; int (*wait_func)(void *data); void *wait_func_data; const char *bus_name; + struct clk *clk; }; #define UNIMAC_MDIO_DRV_NAME "unimac-mdio" -- cgit v1.2.3 From f79ab5d2bced9bd7c0ce86d2aa5b70d053001bb4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Feb 2024 17:41:36 +0200 Subject: wifi: cfg80211: Add KHZ_PER_GHZ to units.h and reuse The KHZ_PER_GHZ might be used by others (with the name aligned with similar constants). Define it in units.h and convert wireless to use it. Signed-off-by: Andy Shevchenko Reviewed-by: Simon Horman Link: https://msgid.link/20240215154136.630029-1-andriy.shevchenko@linux.intel.com Signed-off-by: Johannes Berg --- include/linux/units.h | 5 ++++- net/wireless/reg.c | 7 +++---- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index 45110daaf8d3..00e15de33eca 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -24,10 +24,13 @@ #define NANOHZ_PER_HZ 1000000000UL #define MICROHZ_PER_HZ 1000000UL #define MILLIHZ_PER_HZ 1000UL + #define HZ_PER_KHZ 1000UL -#define KHZ_PER_MHZ 1000UL #define HZ_PER_MHZ 1000000UL +#define KHZ_PER_MHZ 1000UL +#define KHZ_PER_GHZ 1000000UL + #define MILLIWATT_PER_WATT 1000UL #define MICROWATT_PER_MILLIWATT 1000UL #define MICROWATT_PER_WATT 1000000UL diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 50cadbad485f..753f8e9aa4b1 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -57,6 +57,8 @@ #include #include #include +#include + #include #include "core.h" #include "reg.h" @@ -1289,20 +1291,17 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, u32 freq_khz) { -#define ONE_GHZ_IN_KHZ 1000000 /* * From 802.11ad: directional multi-gigabit (DMG): * Pertaining to operation in a frequency band containing a channel * with the Channel starting frequency above 45 GHz. */ - u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ? - 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; + u32 limit = freq_khz > 45 * KHZ_PER_GHZ ? 20 * KHZ_PER_GHZ : 2 * KHZ_PER_GHZ; if (abs(freq_khz - freq_range->start_freq_khz) <= limit) return true; if (abs(freq_khz - freq_range->end_freq_khz) <= limit) return true; return false; -#undef ONE_GHZ_IN_KHZ } /* -- cgit v1.2.3 From 6bd14aee0bd25525ab229acd9bfe536dd8642364 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Feb 2024 13:54:31 +0200 Subject: wifi: mac80211: align ieee80211_mle_get_bss_param_ch_cnt() Align the prototype of ieee80211_mle_get_bss_param_ch_cnt() to also take a u8 * like the other functions, and make it return -1 when the field isn't found, so that mac80211 can check that instead of explicitly open-coding the check. Signed-off-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://msgid.link/20240216135047.583309181bc3.Ia61cb0b4fc034d5ac8fcfaf6f6fb2e115fadafe7@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 11 ++++++----- net/mac80211/mlme.c | 9 +++++---- 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e4322238f273..303c75459897 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4990,17 +4990,18 @@ static inline int ieee80211_mle_get_link_id(const u8 *data) /** * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count - * @mle: the basic multi link element + * @data: pointer to the basic multi link element * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). * * If the BSS parameter change count value can't be found (the presence bit - * for it is clear), 0 will be returned. + * for it is clear), -1 will be returned. */ -static inline u8 -ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle) +static inline int +ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) { + const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); const u8 *common = mle->variable; @@ -5008,7 +5009,7 @@ ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle) common += sizeof(struct ieee80211_mle_basic_common_info); if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) - return 0; + return -1; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 87ffc19770b8..5f2e9f5e1779 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4202,13 +4202,14 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, */ assoc_data->link[link_id].status = WLAN_STATUS_SUCCESS; if (elems->ml_basic) { - if (!(elems->ml_basic->control & - cpu_to_le16(IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT))) { + int bss_param_ch_cnt = + ieee80211_mle_get_bss_param_ch_cnt((const void *)elems->ml_basic); + + if (bss_param_ch_cnt < 0) { ret = false; goto out; } - link->u.mgd.bss_param_ch_cnt = - ieee80211_mle_get_bss_param_ch_cnt(elems->ml_basic); + link->u.mgd.bss_param_ch_cnt = bss_param_ch_cnt; } } else if (elems->parse_error & IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC || !elems->prof || -- cgit v1.2.3 From 894dd84e49ec114a2dde7b312ae4cada40d15bdb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Feb 2024 13:54:32 +0200 Subject: wifi: cfg80211: use ML element parsing helpers Use the existing ML element parsing helpers and add a new one for this (ieee80211_mle_get_mld_id). Signed-off-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://msgid.link/20240216135047.4da47b1f035b.I437a5570ac456449facb0b147851ef24a1e473c2@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 38 ++++++++++++++++++++++++++++++++++++++ net/wireless/scan.c | 41 ++++++++--------------------------------- 2 files changed, 46 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 303c75459897..3385a2cc5b09 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -5115,6 +5115,44 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) return get_unaligned_le16(common); } +/** + * ieee80211_mle_get_mld_id - returns the MLD ID + * @data: pointer to the multi link element + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + * + * If the MLD ID is not present, 0 will be returned. + */ +static inline u8 ieee80211_mle_get_mld_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + + return *common; +} + /** * ieee80211_mle_size_ok - validate multi-link element size * @data: pointer to the element data diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e46dfc71c497..7cf36b8d3ae7 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2833,17 +2833,16 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, struct cfg80211_bss *bss; u8 mld_id, reporter_link_id, bss_change_count; u16 seen_links = 0; - const u8 *pos; u8 i; - if (!ieee80211_mle_size_ok(elem->data + 1, elem->datalen - 1)) + if (!ieee80211_mle_type_ok(elem->data + 1, + IEEE80211_ML_CONTROL_TYPE_BASIC, + elem->datalen - 1)) return; - ml_elem = (void *)elem->data + 1; + ml_elem = (void *)(elem->data + 1); control = le16_to_cpu(ml_elem->control); - if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) != - IEEE80211_ML_CONTROL_TYPE_BASIC) - return; + ml_common_len = ml_elem->variable[0]; /* Must be present when transmitted by an AP (in a probe response) */ if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) || @@ -2851,24 +2850,8 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, !(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) return; - ml_common_len = ml_elem->variable[0]; - - /* length + MLD MAC address */ - pos = ml_elem->variable + 1 + 6; - - reporter_link_id = pos[0]; - pos += 1; - - bss_change_count = pos[0]; - pos += 1; - - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) - pos += 2; - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_EML_CAPA)) - pos += 2; - - /* MLD capabilities and operations */ - pos += 2; + reporter_link_id = ieee80211_mle_get_link_id(elem->data + 1); + bss_change_count = ieee80211_mle_get_bss_param_ch_cnt(elem->data + 1); /* * The MLD ID of the reporting AP is always zero. It is set if the AP @@ -2876,15 +2859,7 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, * relating to a nontransmitted BSS (matching the Multi-BSSID Index, * Draft P802.11be_D3.2, 35.3.4.2) */ - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MLD_ID)) { - mld_id = *pos; - pos += 1; - } else { - mld_id = 0; - } - - /* Extended MLD capabilities and operations */ - pos += 2; + mld_id = ieee80211_mle_get_mld_id(elem->data + 1); /* Fully defrag the ML element for sta information/profile iteration */ mle = cfg80211_defrag_mle(elem, tx_data->ie, tx_data->ielen, gfp); -- cgit v1.2.3 From a3c70a3cf11eb4b6409afc2cce1a3747e1dfe96f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 20 Feb 2024 15:50:01 -0800 Subject: bpf: Shrink size of struct bpf_map/bpf_array. Back in 2018 the commit be95a845cc44 ("bpf: avoid false sharing of map refcount with max_entries") added ____cacheline_aligned to "struct bpf_map" to make sure that fields like refcnt don't share a cache line with max_entries that is used to bounds check map access. That was done to make spectre style attacks harder. The main mitigation is done via code similar to array_index_nospec(), of course. This was an additional precaution. It increased the size of "struct bpf_map" a little, but it's affect on all other maps (like array) is significant, since "struct bpf_map" is typically the first member in other map types. Undo this ____cacheline_aligned tag. Instead move freeze_mutex field around, so that refcnt and max_entries are still in different cache lines. The main effect is seen in sizeof(struct bpf_array) that reduces from 320 to 248 bytes. BEFORE: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ ... char name[16]; /* 96 16 */ /* XXX 16 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */ ... /* size: 256, cachelines: 4, members: 30 */ /* sum members: 232, holes: 1, sum holes: 16 */ /* padding: 8 */ /* paddings: 1, sum paddings: 2 */ } __attribute__((__aligned__(64))); struct bpf_array { struct bpf_map map; /* 0 256 */ ... /* size: 320, cachelines: 5, members: 5 */ /* padding: 48 */ /* paddings: 1, sum paddings: 8 */ } __attribute__((__aligned__(64))); AFTER: struct bpf_map { /* size: 232, cachelines: 4, members: 30 */ /* paddings: 1, sum paddings: 2 */ /* last cacheline: 40 bytes */ }; struct bpf_array { /* size: 248, cachelines: 4, members: 5 */ /* last cacheline: 56 bytes */ }; Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20240220235001.57411-1-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c7aa99b44dbd..814dc913a968 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -251,10 +251,7 @@ struct bpf_list_node_kern { } __attribute__((aligned(8))); struct bpf_map { - /* The first two cachelines with read-mostly members of which some - * are also accessed in fast-path (e.g. ops, max_entries). - */ - const struct bpf_map_ops *ops ____cacheline_aligned; + const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; @@ -276,17 +273,14 @@ struct bpf_map { struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - /* The 3rd and 4th cacheline with misc members to avoid false sharing - * particularly with refcounting. - */ - atomic64_t refcnt ____cacheline_aligned; + struct mutex freeze_mutex; + atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; - struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program * that is going to use this map or by the first program which FD is -- cgit v1.2.3 From ac0c530619cefa68fba816dabbcf6f4ffbf60c3d Mon Sep 17 00:00:00 2001 From: Dimitri Fedrau Date: Sun, 18 Feb 2024 08:57:39 +0100 Subject: net: phy: Support 100/1000BT1 linkmode advertisements Extend helper functions mii_t1_adv_m_mod_linkmode_t and linkmode_adv_to_mii_t1_adv_m_t to support 100BT1 and 1000BT1 linkmode advertisements. Reviewed-by: Andrew Lunn Signed-off-by: Dimitri Fedrau Link: https://lore.kernel.org/r/20240218075753.18067-3-dima.fedrau@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/mdio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index fd8ff310f9eb..68f8d2e970d4 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -373,6 +373,10 @@ static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 l { linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising, lpa & MDIO_AN_T1_ADV_M_B10L); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT, + advertising, lpa & MDIO_AN_T1_ADV_M_100BT1); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT, + advertising, lpa & MDIO_AN_T1_ADV_M_1000BT1); } /** @@ -409,6 +413,10 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising) if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising)) result |= MDIO_AN_T1_ADV_M_B10L; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT, advertising)) + result |= MDIO_AN_T1_ADV_M_100BT1; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT, advertising)) + result |= MDIO_AN_T1_ADV_M_1000BT1; return result; } -- cgit v1.2.3 From e57e4c7f6cc943be3346f938361334bb3634db3d Mon Sep 17 00:00:00 2001 From: Dimitri Fedrau Date: Sun, 18 Feb 2024 08:57:42 +0100 Subject: net: phy: marvell-88q2xxx: add driver for the Marvell 88Q2220 PHY Add a driver for the Marvell 88Q2220. This driver allows to detect the link, switch between 100BASE-T1 and 1000BASE-T1 and switch between master and slave mode. Autonegotiation is supported. Reviewed-by: Andrew Lunn Tested-by: Gregor Herburger Signed-off-by: Dimitri Fedrau Link: https://lore.kernel.org/r/20240218075753.18067-6-dima.fedrau@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/marvell-88q2xxx.c | 210 ++++++++++++++++++++++++++++++++++++-- include/linux/marvell_phy.h | 1 + 2 files changed, 205 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index dcebb4643aff..9829facde253 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -1,11 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 /* * Marvell 88Q2XXX automotive 100BASE-T1/1000BASE-T1 PHY driver + * + * Derived from Marvell Q222x API + * + * Copyright (C) 2024 Liebherr-Electronics and Drives GmbH */ #include #include #include +#define PHY_ID_88Q2220_REVB0 (MARVELL_PHY_ID_88Q2220 | 0x1) + #define MDIO_MMD_AN_MV_STAT 32769 #define MDIO_MMD_AN_MV_STAT_ANEG 0x0100 #define MDIO_MMD_AN_MV_STAT_LOCAL_RX 0x1000 @@ -13,6 +19,11 @@ #define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER 0x4000 #define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT 0x8000 +#define MDIO_MMD_AN_MV_STAT2 32794 +#define MDIO_MMD_AN_MV_STAT2_AN_RESOLVED 0x0800 +#define MDIO_MMD_AN_MV_STAT2_100BT1 0x2000 +#define MDIO_MMD_AN_MV_STAT2_1000BT1 0x4000 + #define MDIO_MMD_PCS_MV_100BT1_STAT1 33032 #define MDIO_MMD_PCS_MV_100BT1_STAT1_IDLE_ERROR 0x00ff #define MDIO_MMD_PCS_MV_100BT1_STAT1_JABBER 0x0100 @@ -29,6 +40,42 @@ #define MDIO_MMD_PCS_MV_RX_STAT 33328 +struct mmd_val { + int devad; + u32 regnum; + u16 val; +}; + +static const struct mmd_val mv88q222x_revb0_init_seq0[] = { + { MDIO_MMD_PCS, 0x8033, 0x6801 }, + { MDIO_MMD_AN, MDIO_AN_T1_CTRL, 0x0 }, + { MDIO_MMD_PMAPMD, MDIO_CTRL1, + MDIO_CTRL1_LPOWER | MDIO_PMA_CTRL1_SPEED1000 }, + { MDIO_MMD_PCS, 0xfe1b, 0x48 }, + { MDIO_MMD_PCS, 0xffe4, 0x6b6 }, + { MDIO_MMD_PMAPMD, MDIO_CTRL1, 0x0 }, + { MDIO_MMD_PCS, MDIO_CTRL1, 0x0 }, +}; + +static const struct mmd_val mv88q222x_revb0_init_seq1[] = { + { MDIO_MMD_PCS, 0xfe79, 0x0 }, + { MDIO_MMD_PCS, 0xfe07, 0x125a }, + { MDIO_MMD_PCS, 0xfe09, 0x1288 }, + { MDIO_MMD_PCS, 0xfe08, 0x2588 }, + { MDIO_MMD_PCS, 0xfe11, 0x1105 }, + { MDIO_MMD_PCS, 0xfe72, 0x042c }, + { MDIO_MMD_PCS, 0xfbba, 0xcb2 }, + { MDIO_MMD_PCS, 0xfbbb, 0xc4a }, + { MDIO_MMD_AN, 0x8032, 0x2020 }, + { MDIO_MMD_AN, 0x8031, 0xa28 }, + { MDIO_MMD_AN, 0x8031, 0xc28 }, + { MDIO_MMD_PCS, 0xffdb, 0xfc10 }, + { MDIO_MMD_PCS, 0xfe1b, 0x58 }, + { MDIO_MMD_PCS, 0xfe79, 0x4 }, + { MDIO_MMD_PCS, 0xfe5f, 0xe8 }, + { MDIO_MMD_PCS, 0xfe05, 0x755c }, +}; + static int mv88q2xxx_soft_reset(struct phy_device *phydev) { int ret; @@ -125,24 +172,90 @@ out: static int mv88q2xxx_read_link(struct phy_device *phydev) { - int ret; - /* The 88Q2XXX PHYs do not have the PMA/PMD status register available, * therefore we need to read the link status from the vendor specific * registers depending on the speed. */ + if (phydev->speed == SPEED_1000) - ret = mv88q2xxx_read_link_gbit(phydev); + return mv88q2xxx_read_link_gbit(phydev); + else if (phydev->speed == SPEED_100) + return mv88q2xxx_read_link_100m(phydev); + + phydev->link = false; + return 0; +} + +static int mv88q2xxx_read_master_slave_state(struct phy_device *phydev) +{ + int ret; + + phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN; + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_MMD_AN_MV_STAT); + if (ret < 0) + return ret; + + if (ret & MDIO_MMD_AN_MV_STAT_LOCAL_MASTER) + phydev->master_slave_state = MASTER_SLAVE_STATE_MASTER; else - ret = mv88q2xxx_read_link_100m(phydev); + phydev->master_slave_state = MASTER_SLAVE_STATE_SLAVE; - return ret; + return 0; +} + +static int mv88q2xxx_read_aneg_speed(struct phy_device *phydev) +{ + int ret; + + phydev->speed = SPEED_UNKNOWN; + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_MMD_AN_MV_STAT2); + if (ret < 0) + return ret; + + if (!(ret & MDIO_MMD_AN_MV_STAT2_AN_RESOLVED)) + return 0; + + if (ret & MDIO_MMD_AN_MV_STAT2_100BT1) + phydev->speed = SPEED_100; + else if (ret & MDIO_MMD_AN_MV_STAT2_1000BT1) + phydev->speed = SPEED_1000; + + return 0; } static int mv88q2xxx_read_status(struct phy_device *phydev) { int ret; + if (phydev->autoneg == AUTONEG_ENABLE) { + /* We have to get the negotiated speed first, otherwise we are + * not able to read the link. + */ + ret = mv88q2xxx_read_aneg_speed(phydev); + if (ret < 0) + return ret; + + ret = mv88q2xxx_read_link(phydev); + if (ret < 0) + return ret; + + ret = genphy_c45_read_lpa(phydev); + if (ret < 0) + return ret; + + ret = genphy_c45_baset1_read_status(phydev); + if (ret < 0) + return ret; + + ret = mv88q2xxx_read_master_slave_state(phydev); + if (ret < 0) + return ret; + + phy_resolve_aneg_linkmode(phydev); + + return 0; + } + ret = mv88q2xxx_read_link(phydev); if (ret < 0) return ret; @@ -171,7 +284,9 @@ static int mv88q2xxx_get_features(struct phy_device *phydev) * sequence provided by Marvell. Disable it for now until a proper * workaround is found or a new PHY revision is released. */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported); + if (phydev->drv->phy_id == MARVELL_PHY_ID_88Q2110) + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported); return 0; } @@ -241,6 +356,75 @@ static int mv88q2xxx_get_sqi_max(struct phy_device *phydev) return 15; } +static int mv88q222x_soft_reset(struct phy_device *phydev) +{ + int ret; + + /* Enable RESET of DCL */ + if (phydev->autoneg == AUTONEG_ENABLE || phydev->speed == SPEED_1000) { + ret = phy_write_mmd(phydev, MDIO_MMD_PCS, 0xfe1b, 0x48); + if (ret < 0) + return ret; + } + + ret = phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_1000BT1_CTRL, + MDIO_PCS_1000BT1_CTRL_RESET); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_PCS, 0xffe4, 0xc); + if (ret < 0) + return ret; + + /* Disable RESET of DCL */ + if (phydev->autoneg == AUTONEG_ENABLE || phydev->speed == SPEED_1000) + return phy_write_mmd(phydev, MDIO_MMD_PCS, 0xfe1b, 0x58); + + return 0; +} + +static int mv88q222x_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_c45_config_aneg(phydev); + if (ret) + return ret; + + return mv88q222x_soft_reset(phydev); +} + +static int mv88q222x_revb0_config_init(struct phy_device *phydev) +{ + int ret, i; + + for (i = 0; i < ARRAY_SIZE(mv88q222x_revb0_init_seq0); i++) { + ret = phy_write_mmd(phydev, mv88q222x_revb0_init_seq0[i].devad, + mv88q222x_revb0_init_seq0[i].regnum, + mv88q222x_revb0_init_seq0[i].val); + if (ret < 0) + return ret; + } + + usleep_range(5000, 10000); + + for (i = 0; i < ARRAY_SIZE(mv88q222x_revb0_init_seq1); i++) { + ret = phy_write_mmd(phydev, mv88q222x_revb0_init_seq1[i].devad, + mv88q222x_revb0_init_seq1[i].regnum, + mv88q222x_revb0_init_seq1[i].val); + if (ret < 0) + return ret; + } + + /* The 88Q2XXX PHYs do have the extended ability register available, but + * register MDIO_PMA_EXTABLE where they should signalize it does not + * work according to specification. Therefore, we force it here. + */ + phydev->pma_extable = MDIO_PMA_EXTABLE_BT1; + + return 0; +} + static struct phy_driver mv88q2xxx_driver[] = { { .phy_id = MARVELL_PHY_ID_88Q2110, @@ -255,12 +439,26 @@ static struct phy_driver mv88q2xxx_driver[] = { .get_sqi = mv88q2xxx_get_sqi, .get_sqi_max = mv88q2xxx_get_sqi_max, }, + { + PHY_ID_MATCH_EXACT(PHY_ID_88Q2220_REVB0), + .name = "mv88q2220", + .get_features = mv88q2xxx_get_features, + .config_aneg = mv88q222x_config_aneg, + .aneg_done = genphy_c45_aneg_done, + .config_init = mv88q222x_revb0_config_init, + .read_status = mv88q2xxx_read_status, + .soft_reset = mv88q222x_soft_reset, + .set_loopback = genphy_c45_loopback, + .get_sqi = mv88q2xxx_get_sqi, + .get_sqi_max = mv88q2xxx_get_sqi_max, + }, }; module_phy_driver(mv88q2xxx_driver); static struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { { MARVELL_PHY_ID_88Q2110, MARVELL_PHY_ID_MASK }, + { PHY_ID_MATCH_EXACT(PHY_ID_88Q2220_REVB0), }, { /*sentinel*/ } }; MODULE_DEVICE_TABLE(mdio, mv88q2xxx_tbl); diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 9b54c4f0677f..693eba9869e4 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -26,6 +26,7 @@ #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 #define MARVELL_PHY_ID_88Q2110 0x002b0980 +#define MARVELL_PHY_ID_88Q2220 0x002b0b20 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 -- cgit v1.2.3 From f796feabb9f5b1e5c48780a7a0023ab4b82336dd Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Feb 2024 12:00:01 +0100 Subject: udp: add local "peek offset enabled" flag We want to re-organize the struct sock layout. The sk_peek_off field location is problematic, as most protocols want it in the RX read area, while UDP wants it on a cacheline different from sk_receive_queue. Create a local (inside udp_sock) copy of the 'peek offset is enabled' flag and place it inside the same cacheline of reader_queue. Check such flag before reading sk_peek_off. This will save potential false sharing and cache misses in the fast-path. Tested under UDP flood with small packets. The struct sock layout update causes a 4% performance drop, and this patch restores completely the original tput. Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/67ab679c15fbf49fa05b3ffe05d91c47ab84f147.1708426665.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/udp.h | 10 ++++++++++ net/ipv4/af_inet.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/af_inet6.c | 2 +- 4 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index d04188714dca..3748e82b627b 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -92,6 +92,9 @@ struct udp_sock { /* This fields follows rcvbuf value, and is touched by udp_recvmsg */ int forward_threshold; + + /* Cache friendly copy of sk->sk_peek_off >= 0 */ + bool peeking_with_offset; }; #define udp_test_bit(nr, sk) \ @@ -109,6 +112,13 @@ struct udp_sock { #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) +static inline int udp_set_peek_off(struct sock *sk, int val) +{ + sk_set_peek_off(sk, val); + WRITE_ONCE(udp_sk(sk)->peeking_with_offset, val >= 0); + return 0; +} + static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { udp_assign_bit(NO_CHECK6_TX, sk, val); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ad278009e469..5daebdcbca32 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1103,7 +1103,7 @@ const struct proto_ops inet_dgram_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f631b0a21af4..38cce7cc51f6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1589,7 +1589,7 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { + if (unlikely(READ_ONCE(udp_sk(sk)->peeking_with_offset))) { bool slow = lock_sock_fast(sk); sk_peek_offset_bwd(sk, len); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 959bfd9f6344..b90d46533cdc 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -736,7 +736,7 @@ const struct proto_ops inet6_dgram_ops = { .recvmsg = inet6_recvmsg, /* retpoline's sake */ .read_skb = udp_read_skb, .mmap = sock_no_mmap, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif -- cgit v1.2.3 From 025f8ad20f2e3264d11683aa9cbbf0083eefbdcd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 22 Feb 2024 15:03:10 +0100 Subject: net: mpls: error out if inner headers are not set mpls_gso_segment() assumes skb_inner_network_header() returns a valid result: mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) goto out; if (unlikely(!pskb_may_pull(skb, mpls_hlen))) With syzbot reproducer, skb_inner_network_header() yields 0, skb_network_header() returns 108, so this will "pskb_may_pull(skb, -108)))" which triggers a newly added DEBUG_NET_WARN_ON_ONCE() check: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 5068 at include/linux/skbuff.h:2723 pskb_may_pull_reason include/linux/skbuff.h:2723 [inline] WARNING: CPU: 0 PID: 5068 at include/linux/skbuff.h:2723 pskb_may_pull include/linux/skbuff.h:2739 [inline] WARNING: CPU: 0 PID: 5068 at include/linux/skbuff.h:2723 mpls_gso_segment+0x773/0xaa0 net/mpls/mpls_gso.c:34 [..] skb_mac_gso_segment+0x383/0x740 net/core/gso.c:53 nsh_gso_segment+0x40a/0xad0 net/nsh/nsh.c:108 skb_mac_gso_segment+0x383/0x740 net/core/gso.c:53 __skb_gso_segment+0x324/0x4c0 net/core/gso.c:124 skb_gso_segment include/net/gso.h:83 [inline] [..] sch_direct_xmit+0x11a/0x5f0 net/sched/sch_generic.c:327 [..] packet_sendmsg+0x46a9/0x6130 net/packet/af_packet.c:3113 [..] First iteration of this patch made mpls_hlen signed and changed test to error out to "mpls_hlen <= 0 || ..". Eric Dumazet said: > I was thinking about adding a debug check in skb_inner_network_header() > if inner_network_header is zero (that would mean it is not 'set' yet), > but this would trigger even after your patch. So add new skb_inner_network_header_was_set() helper and use that. The syzbot reproducer injects data via packet socket. The skb that gets allocated and passed down the stack has ->protocol set to NSH (0x894f) and gso_type set to SKB_GSO_UDP | SKB_GSO_DODGY. This gets passed to skb_mac_gso_segment(), which sees NSH as ptype to find a callback for. nsh_gso_segment() retrieves next type: proto = tun_p_to_eth_p(nsh_hdr(skb)->np); ... which is MPLS (TUN_P_MPLS_UC). It updates skb->protocol and then calls mpls_gso_segment(). Inner offsets are all 0, so mpls_gso_segment() ends up with a negative header size. In case more callers rely on silent handling of such large may_pull values we could also 'legalize' this behaviour, either replacing the debug check with (len > INT_MAX) test or removing it and instead adding a comment before existing if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; test in pskb_may_pull_reason(), saying that this check also implicitly takes care of callers that miscompute header sizes. Cc: Simon Horman Fixes: 219eee9c0d16 ("net: skbuff: add overflow debug check to pull/push helpers") Reported-by: syzbot+99d15fcdb0132a1e1a82@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/00000000000043b1310611e388aa@google.com/raw Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20240222140321.14080-1-fw@strlen.de Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 +++++ net/mpls/mpls_gso.c | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 28c7cb7ce251..1470b74fb6d2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2894,6 +2894,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) +{ + return skb->inner_network_header > 0; +} + static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 533d082f0701..45d1e6a157fc 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -27,6 +27,9 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, __be16 mpls_protocol; unsigned int mpls_hlen; + if (!skb_inner_network_header_was_set(skb)) + goto out; + skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) -- cgit v1.2.3 From 8afc7a78d55de726b2747d7775c54def79509ec5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Feb 2024 10:50:10 +0000 Subject: ipv6: prepare inet6_fill_ifinfo() for RCU protection We want to use RCU protection instead of RTNL for inet6_fill_ifinfo(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- net/core/dev.c | 4 ++-- net/ipv6/addrconf.c | 11 +++++++---- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f07c8374f29c..09023e44db4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4354,8 +4354,10 @@ static inline bool netif_testing(const struct net_device *dev) */ static inline bool netif_oper_up(const struct net_device *dev) { - return (dev->operstate == IF_OPER_UP || - dev->operstate == IF_OPER_UNKNOWN /* backward compat */); + unsigned int operstate = READ_ONCE(dev->operstate); + + return operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN /* backward compat */; } /** diff --git a/net/core/dev.c b/net/core/dev.c index 0628d8ff1ed9..275fd5259a4a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8632,12 +8632,12 @@ unsigned int dev_get_flags(const struct net_device *dev) { unsigned int flags; - flags = (dev->flags & ~(IFF_PROMISC | + flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | - (dev->gflags & (IFF_PROMISC | + (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a56dad307fe3..daa81556d118 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6062,6 +6062,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; + int ifindex, iflink; void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); @@ -6072,16 +6073,18 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, hdr->ifi_family = AF_INET6; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; - hdr->ifi_index = dev->ifindex; + ifindex = READ_ONCE(dev->ifindex); + hdr->ifi_index = ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; + iflink = dev_get_iflink(dev); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || - nla_put_u32(skb, IFLA_MTU, dev->mtu) || - (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || + nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || + (ifindex != iflink && + nla_put_u32(skb, IFLA_LINK, iflink)) || nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; -- cgit v1.2.3 From 386520e0ecc01004d3a29c70c5a77d4bbf8a8420 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Feb 2024 10:50:15 +0000 Subject: rtnetlink: add RTNL_FLAG_DUMP_UNLOCKED flag Similarly to RTNL_FLAG_DOIT_UNLOCKED, this new flag allows dump operations registered via rtnl_register() or rtnl_register_module() to opt-out from RTNL protection. Signed-off-by: Eric Dumazet Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 ++ include/net/rtnetlink.h | 1 + net/core/rtnetlink.c | 2 ++ net/netlink/af_netlink.c | 3 +++ 4 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1a4445bf2ab9..5df7340d4dab 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -291,6 +291,7 @@ struct netlink_callback { u16 answer_flags; u32 min_dump_alloc; unsigned int prev_seq, seq; + int flags; bool strict_check; union { u8 ctx[48]; @@ -323,6 +324,7 @@ struct netlink_dump_control { void *data; struct module *module; u32 min_dump_alloc; + int flags; }; int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 6506221c5fe3..3bfb80bad173 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -12,6 +12,7 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), + RTNL_FLAG_DUMP_UNLOCKED = BIT(2), }; enum rtnl_kinds { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 060543fe7919..1b26dfa5668d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -6532,6 +6532,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, } owner = link->owner; dumpit = link->dumpit; + flags = link->flags; if (type == RTM_GETLINK - RTM_BASE) min_dump_alloc = rtnl_calcit(skb, nlh); @@ -6549,6 +6550,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, .dump = dumpit, .min_dump_alloc = min_dump_alloc, .module = owner, + .flags = flags, }; err = netlink_dump_start(rtnl, skb, nlh, &c); /* netlink_dump_start() will keep a reference on diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 84cad7be6d43..be5792b638aa 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2261,6 +2261,8 @@ static int netlink_dump(struct sock *sk, bool lock_taken) cb->extack = &extack; + if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED) + extra_mutex = NULL; if (extra_mutex) mutex_lock(extra_mutex); nlk->dump_done_errno = cb->dump(skb, cb); @@ -2355,6 +2357,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; + cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); -- cgit v1.2.3 From 416eb60317c64676d158dffea150762930ec008f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 23 Feb 2024 10:01:46 +0100 Subject: bitfield: suppress "dubious: x & !y" sparse warning There's a somewhat common pattern of using FIELD_PREP() even for single bits, e.g. cmd->info1 |= FIELD_PREP(HTT_SRNG_SETUP_CMD_INFO1_RING_FLAGS_MSI_SWAP, !!(params.flags & HAL_SRNG_FLAGS_MSI_SWAP)); which might as well be written as if (params.flags & HAL_SRNG_FLAGS_MSI_SWAP) cmd->info1 |= HTT_SRNG_SETUP_CMD_INFO1_RING_FLAGS_MSI_SWAP; (since info1 is fully initialized to start with), but in a long chain of FIELD_PREP() this really seems fine. However, it triggers a sparse warning, in the check in the macro for whether a constant value fits into the mask, as this contains a "& (_val)". In this case, this really is always intentional, so just suppress the warning by adding "0+" to the expression, indicating explicitly that this is correct. Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo Link: https://msgid.link/20240223100146.d243b6b1a9a1.I033828b1187c6bccf086e31400f7e933bb8373e7@changeid --- include/linux/bitfield.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index ebfa12f69501..63928f173223 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -66,7 +66,8 @@ _pfx "mask is not constant"); \ BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ - ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ + ~((_mask) >> __bf_shf(_mask)) & \ + (0 + (_val)) : 0, \ _pfx "value too large for the field"); \ BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ __bf_cast_unsigned(_reg, ~0ull), \ -- cgit v1.2.3 From 292fac464b012200c4e99d08974fed3bc087b848 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 26 Feb 2024 19:29:15 -0600 Subject: net: ethtool: eee: Remove legacy _u32 from keee All MAC drivers have been converted to use the link mode members of keee. So remove the _u32 values, and the code in the ethtool core to convert the legacy _u32 values to link modes. Reviewed-by: Simon Horman Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 --- net/ethtool/eee.c | 31 ++++--------------------------- net/ethtool/ioctl.c | 29 ++++++++++------------------- 3 files changed, 14 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b90c33607594..9901e563f706 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -226,9 +226,6 @@ struct ethtool_keee { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertised); - u32 supported_u32; - u32 advertised_u32; - u32 lp_advertised_u32; u32 tx_lpi_timer; bool tx_lpi_enabled; bool eee_active; diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index db6faa18fe41..bf398973eb8a 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -4,9 +4,6 @@ #include "common.h" #include "bitset.h" -#define EEE_MODES_COUNT \ - (sizeof_field(struct ethtool_keee, supported_u32) * BITS_PER_BYTE) - struct eee_req_info { struct ethnl_req_info base; }; @@ -41,15 +38,6 @@ static int eee_prepare_data(const struct ethnl_req_info *req_base, ret = dev->ethtool_ops->get_eee(dev, eee); ethnl_ops_complete(dev); - if (!ret && !ethtool_eee_use_linkmodes(eee)) { - ethtool_convert_legacy_u32_to_link_mode(eee->supported, - eee->supported_u32); - ethtool_convert_legacy_u32_to_link_mode(eee->advertised, - eee->advertised_u32); - ethtool_convert_legacy_u32_to_link_mode(eee->lp_advertised, - eee->lp_advertised_u32); - } - return ret; } @@ -62,11 +50,6 @@ static int eee_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; - BUILD_BUG_ON(sizeof(eee->advertised_u32) * BITS_PER_BYTE != - EEE_MODES_COUNT); - BUILD_BUG_ON(sizeof(eee->lp_advertised_u32) * BITS_PER_BYTE != - EEE_MODES_COUNT); - /* MODES_OURS */ ret = ethnl_bitset_size(eee->advertised, eee->supported, __ETHTOOL_LINK_MODE_MASK_NBITS, @@ -154,16 +137,10 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) if (ret < 0) return ret; - if (ethtool_eee_use_linkmodes(&eee)) { - ret = ethnl_update_bitset(eee.advertised, - __ETHTOOL_LINK_MODE_MASK_NBITS, - tb[ETHTOOL_A_EEE_MODES_OURS], - link_mode_names, info->extack, &mod); - } else { - ret = ethnl_update_bitset32(&eee.advertised_u32, EEE_MODES_COUNT, - tb[ETHTOOL_A_EEE_MODES_OURS], - link_mode_names, info->extack, &mod); - } + ret = ethnl_update_bitset(eee.advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS, + tb[ETHTOOL_A_EEE_MODES_OURS], + link_mode_names, info->extack, &mod); if (ret < 0) return ret; ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index b419969c0dcb..317308bdbda9 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1514,9 +1514,6 @@ static void eee_to_keee(struct ethtool_keee *keee, { memset(keee, 0, sizeof(*keee)); - keee->supported_u32 = eee->supported; - keee->advertised_u32 = eee->advertised; - keee->lp_advertised_u32 = eee->lp_advertised; keee->eee_active = eee->eee_active; keee->eee_enabled = eee->eee_enabled; keee->tx_lpi_enabled = eee->tx_lpi_enabled; @@ -1533,6 +1530,8 @@ static void eee_to_keee(struct ethtool_keee *keee, static void keee_to_eee(struct ethtool_eee *eee, const struct ethtool_keee *keee) { + bool overflow; + memset(eee, 0, sizeof(*eee)); eee->eee_active = keee->eee_active; @@ -1540,22 +1539,14 @@ static void keee_to_eee(struct ethtool_eee *eee, eee->tx_lpi_enabled = keee->tx_lpi_enabled; eee->tx_lpi_timer = keee->tx_lpi_timer; - if (ethtool_eee_use_linkmodes(keee)) { - bool overflow; - - overflow = !ethtool_convert_link_mode_to_legacy_u32(&eee->supported, - keee->supported); - ethtool_convert_link_mode_to_legacy_u32(&eee->advertised, - keee->advertised); - ethtool_convert_link_mode_to_legacy_u32(&eee->lp_advertised, - keee->lp_advertised); - if (overflow) - pr_warn("Ethtool ioctl interface doesn't support passing EEE linkmodes beyond bit 32\n"); - } else { - eee->supported = keee->supported_u32; - eee->advertised = keee->advertised_u32; - eee->lp_advertised = keee->lp_advertised_u32; - } + overflow = !ethtool_convert_link_mode_to_legacy_u32(&eee->supported, + keee->supported); + ethtool_convert_link_mode_to_legacy_u32(&eee->advertised, + keee->advertised); + ethtool_convert_link_mode_to_legacy_u32(&eee->lp_advertised, + keee->lp_advertised); + if (overflow) + pr_warn("Ethtool ioctl interface doesn't support passing EEE linkmodes beyond bit 32\n"); } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) -- cgit v1.2.3 From 0598f8f3bb77893a13105d47bb7dfe42f1dc1f4e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Feb 2024 09:24:09 +0000 Subject: inet: annotate devconf data-races Add READ_ONCE() in ipv4_devconf_get() and corresponding WRITE_ONCE() in ipv4_devconf_set() Add IPV4_DEVCONF_RO() and IPV4_DEVCONF_ALL_RO() macros, and use them when reading devconf fields. Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20240227092411.2315725-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 14 ++++++++------ net/ipv4/devinet.c | 21 +++++++++++---------- net/ipv4/igmp.c | 4 ++-- net/ipv4/proc.c | 2 +- net/ipv4/route.c | 4 ++-- 5 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ddb27fc0ee8c..cb5280e6cc21 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -53,13 +53,15 @@ struct in_device { }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) +#define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) +#define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) -static inline int ipv4_devconf_get(struct in_device *in_dev, int index) +static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; - return in_dev->cnf.data[index]; + return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, @@ -67,7 +69,7 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index, { index--; set_bit(index, in_dev->cnf.state); - in_dev->cnf.data[index] = val; + WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) @@ -81,18 +83,18 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ - (IPV4_DEVCONF_ALL(net, attr) || \ + (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ - (max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \ + (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bc74f131fe4d..ca75d0fff1d1 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1982,7 +1982,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) - ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } @@ -2068,9 +2068,9 @@ static int inet_netconf_msgsize_devconf(int type) } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, - struct ipv4_devconf *devconf, u32 portid, - u32 seq, int event, unsigned int flags, - int type) + const struct ipv4_devconf *devconf, + u32 portid, u32 seq, int event, + unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; @@ -2095,27 +2095,28 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, - IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, - IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, - IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, - IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) + IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, - IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) + IPV4_DEVCONF_RO(*devconf, + IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index efeeca2b1328..717e97a389a8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -120,12 +120,12 @@ */ #define IGMP_V1_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5f4654ebff48..914bc9c35cc7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -395,7 +395,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) seq_printf(seq, " %s", snmp4_ipstats_list[i].name); seq_printf(seq, "\nIp: %d %d", - IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, + IPV4_DEVCONF_ALL_RO(net, FORWARDING) ? 1 : 2, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b512288d6fcc..c8f76f56dc16 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2313,7 +2313,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ - if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) + if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } @@ -2993,7 +2993,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); -- cgit v1.2.3 From 99123622050f10ca9148a0fffba2de0afd6cdfff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Feb 2024 19:27:21 +0000 Subject: tcp: remove some holes in struct tcp_sock By moving some fields around, this patch shrinks holes size from 56 to 32, saving 24 bytes on 64bit arches. After the patch pahole gives the following for 'struct tcp_sock': /* size: 2304, cachelines: 36, members: 162 */ /* sum members: 2234, holes: 6, sum holes: 32 */ /* sum bitfield members: 34 bits, bit holes: 5, sum bit holes: 14 bits */ /* padding: 32 */ /* paddings: 3, sum paddings: 10 */ /* forced alignments: 1, forced holes: 1, sum forced holes: 12 */ Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20240227192721.3558982-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/tcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a1c47a6d69b0..988a30ef6bfe 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -264,10 +264,10 @@ struct tcp_sock { u32 pushed_seq; /* Last pushed seq, required to talk to windows */ u32 lsndtime; u32 mdev_us; /* medium deviation */ + u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ u64 tcp_mstamp; /* most recent packet received/sent */ - u32 rtt_seq; /* sequence number to update rttvar */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set @@ -350,7 +350,6 @@ struct tcp_sock { u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups * total number of DSACK blocks received */ - u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ u32 compressed_ack_rcv_nxt; struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ @@ -384,12 +383,12 @@ struct tcp_sock { syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ + u8 keepalive_probes; /* num of allowed keep alive probes */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ /* RTT measurement */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ - u8 keepalive_probes; /* num of allowed keep alive probes */ u32 reord_seen; /* number of data packet reordering events */ /* @@ -402,6 +401,7 @@ struct tcp_sock { u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ + u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ struct hrtimer pacing_timer; struct hrtimer compressed_ack_timer; @@ -477,8 +477,8 @@ struct tcp_sock { bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) - bool (*smc_hs_congested)(const struct sock *sk); bool syn_smc; /* SYN includes SMC */ + bool (*smc_hs_congested)(const struct sock *sk); #endif #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) -- cgit v1.2.3 From 096361b15577a583afcc28179a08c75cf95e9dae Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 28 Feb 2024 13:54:25 +0000 Subject: ipv6: add ipv6_devconf_read_txrx cacheline_group IPv6 TX and RX fast path use the following fields: - disable_ipv6 - hop_limit - mtu6 - forwarding - disable_policy - proxy_ndp Place them in a group to increase data locality. Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/ipv6.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ef3aa060a289..383a0ea2ab91 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -3,6 +3,7 @@ #define _IPV6_H #include +#include #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) #define ipv6_authlen(p) (((p)->hdrlen+2) << 2) @@ -10,9 +11,16 @@ * This structure contains configuration options per IPv6 link. */ struct ipv6_devconf { - __s32 forwarding; + /* RX & TX fastpath fields. */ + __cacheline_group_begin(ipv6_devconf_read_txrx); + __s32 disable_ipv6; __s32 hop_limit; __s32 mtu6; + __s32 forwarding; + __s32 disable_policy; + __s32 proxy_ndp; + __cacheline_group_end(ipv6_devconf_read_txrx); + __s32 accept_ra; __s32 accept_redirects; __s32 autoconf; @@ -45,7 +53,6 @@ struct ipv6_devconf { __s32 accept_ra_rt_info_max_plen; #endif #endif - __s32 proxy_ndp; __s32 accept_source_route; __s32 accept_ra_from_local; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -55,7 +62,6 @@ struct ipv6_devconf { #ifdef CONFIG_IPV6_MROUTE atomic_t mc_forwarding; #endif - __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; @@ -76,7 +82,6 @@ struct ipv6_devconf { #endif __u32 enhanced_dad; __u32 addr_gen_mode; - __s32 disable_policy; __s32 ndisc_tclass; __s32 rpl_seg_enabled; __u32 ioam6_id; -- cgit v1.2.3 From f29f9199c2d2b3c258f577f438885288016847ed Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 28 Feb 2024 15:05:29 +0100 Subject: Simplify net_dbg_ratelimited() dummy There is no need to wrap calls to the no_printk() helper inside an always-false check, as no_printk() already does that internally. Signed-off-by: Geert Uytterhoeven Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/net.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index c9b4a63791a4..15df6d5f27a7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -299,10 +299,7 @@ do { \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else #define net_dbg_ratelimited(fmt, ...) \ - do { \ - if (0) \ - no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ - } while (0) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #define net_get_random_once(buf, nbytes) \ -- cgit v1.2.3 From cc15bd10e716fcb472d611f24d76c795acb0f8c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 Feb 2024 09:39:08 +0000 Subject: net: adopt skb_network_header_len() more broadly (skb_transport_header(skb) - skb_network_header(skb)) can be replaced by skb_network_header_len(skb) Add a DEBUG_NET_WARN_ON_ONCE() in skb_network_header_len() to catch cases were the transport_header was not set. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +-- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 3 +-- drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 2 +- drivers/net/wireless/intel/iwlwifi/queue/tx.c | 2 +- include/linux/skbuff.h | 1 + 7 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index adcee8d9d6d9..c9b6acd8c892 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3621,8 +3621,7 @@ static u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb, ((skb->protocol == cpu_to_be16(ETH_P_8021Q)) << ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT)); - pbd->ip_hlen_w = (skb_transport_header(skb) - - skb_network_header(skb)) >> 1; + pbd->ip_hlen_w = skb_network_header_len(skb) >> 1; hlen += pbd->ip_hlen_w; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a67b13869016..3fada49b8ae2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13213,7 +13213,7 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, goto out_err; /* IPLEN and EIPLEN can support at most 127 dwords */ - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len & ~(127 * 4)) goto out_err; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 245c458e38ae..aefec6bd3b67 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4428,7 +4428,7 @@ static netdev_features_t iavf_features_check(struct sk_buff *skb, goto out_err; /* IPLEN and EIPLEN can support at most 127 dwords */ - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len & ~(127 * 4)) goto out_err; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index e502f4ee9e1f..782ddc8c296b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1015,8 +1015,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, netdev_features_t netdev_flags = NETIF_F_CSUM_MASK | NETIF_F_SG; u8 tid; - snap_ip_tcp = 8 + skb_transport_header(skb) - skb_network_header(skb) + - tcp_hdrlen(skb); + snap_ip_tcp = 8 + skb_network_header_len(skb) + tcp_hdrlen(skb); if (!mvmsta->max_amsdu_len || !ieee80211_is_data_qos(hdr->frame_control) || diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 6c2b37e56c78..fa8eba47dc4c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1331,7 +1331,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, trans->txqs.tfd.size, &dev_cmd->hdr, IWL_FIRST_TB_SIZE + tb1_len, 0); - ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); + ip_hdrlen = skb_network_header_len(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len - iv_len; amsdu_pad = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index d3bde2d010b7..33973a60d0bf 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -353,7 +353,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr, start_len, 0); - ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); + ip_hdrlen = skb_network_header_len(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len; amsdu_pad = 0; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1470b74fb6d2..d577e0bee18d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3036,6 +3036,7 @@ static inline int skb_transport_offset(const struct sk_buff *skb) static inline u32 skb_network_header_len(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } -- cgit v1.2.3 From 187e2af05abe6bf80581490239c449456627d17a Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Sat, 24 Feb 2024 14:34:17 -0800 Subject: bpf: struct_ops supports more than one page for trampolines. The BPF struct_ops previously only allowed one page of trampolines. Each function pointer of a struct_ops is implemented by a struct_ops bpf program. Each struct_ops bpf program requires a trampoline. The following selftest patch shows each page can hold a little more than 20 trampolines. While one page is more than enough for the tcp-cc usecase, the sched_ext use case shows that one page is not always enough and hits the one page limit. This patch overcomes the one page limit by allocating another page when needed and it is limited to a total of MAX_IMAGE_PAGES (8) pages which is more than enough for reasonable usages. The variable st_map->image has been changed to st_map->image_pages, and its type has been changed to an array of pointers to pages. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240224223418.526631-3-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 +- kernel/bpf/bpf_struct_ops.c | 130 ++++++++++++++++++++++++++++------------- net/bpf/bpf_dummy_struct_ops.c | 12 ++-- 3 files changed, 96 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 814dc913a968..785660810e6a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1763,7 +1763,9 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, void *stub_func, - void *image, void *image_end); + void **image, u32 *image_off, + bool allow_alloc); +void bpf_struct_ops_image_free(void *image); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 07e554c191d1..43356faaa057 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -18,6 +18,8 @@ struct bpf_struct_ops_value { char data[] ____cacheline_aligned_in_smp; }; +#define MAX_TRAMP_IMAGE_PAGES 8 + struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; @@ -30,12 +32,11 @@ struct bpf_struct_ops_map { */ struct bpf_link **links; u32 links_cnt; - /* image is a page that has all the trampolines + u32 image_pages_cnt; + /* image_pages is an array of pages that has all the trampolines * that stores the func args before calling the bpf_prog. - * A PAGE_SIZE "image" is enough to store all trampoline for - * "links[]". */ - void *image; + void *image_pages[MAX_TRAMP_IMAGE_PAGES]; /* The owner moduler's btf. */ struct btf *btf; /* uvalue->data stores the kernel struct @@ -116,6 +117,31 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } +static void *bpf_struct_ops_image_alloc(void) +{ + void *image; + int err; + + err = bpf_jit_charge_modmem(PAGE_SIZE); + if (err) + return ERR_PTR(err); + image = arch_alloc_bpf_trampoline(PAGE_SIZE); + if (!image) { + bpf_jit_uncharge_modmem(PAGE_SIZE); + return ERR_PTR(-ENOMEM); + } + + return image; +} + +void bpf_struct_ops_image_free(void *image) +{ + if (image) { + arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_jit_uncharge_modmem(PAGE_SIZE); + } +} + #define MAYBE_NULL_SUFFIX "__nullable" #define MAX_STUB_NAME 128 @@ -461,6 +487,15 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) } } +static void bpf_struct_ops_map_free_image(struct bpf_struct_ops_map *st_map) +{ + int i; + + for (i = 0; i < st_map->image_pages_cnt; i++) + bpf_struct_ops_image_free(st_map->image_pages[i]); + st_map->image_pages_cnt = 0; +} + static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; @@ -506,9 +541,12 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *stub_func, void *image, void *image_end) + void *stub_func, + void **_image, u32 *_image_off, + bool allow_alloc) { - u32 flags = BPF_TRAMP_F_INDIRECT; + u32 image_off = *_image_off, flags = BPF_TRAMP_F_INDIRECT; + void *image = *_image; int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; @@ -518,12 +556,32 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, flags |= BPF_TRAMP_F_RET_FENTRY_RET; size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); - if (size < 0) - return size; - if (size > (unsigned long)image_end - (unsigned long)image) - return -E2BIG; - return arch_prepare_bpf_trampoline(NULL, image, image_end, + if (size <= 0) + return size ? : -EFAULT; + + /* Allocate image buffer if necessary */ + if (!image || size > PAGE_SIZE - image_off) { + if (!allow_alloc) + return -E2BIG; + + image = bpf_struct_ops_image_alloc(); + if (IS_ERR(image)) + return PTR_ERR(image); + image_off = 0; + } + + size = arch_prepare_bpf_trampoline(NULL, image + image_off, + image + PAGE_SIZE, model, flags, tlinks, stub_func); + if (size <= 0) { + if (image != *_image) + bpf_struct_ops_image_free(image); + return size ? : -EFAULT; + } + + *_image = image; + *_image_off = image_off + size; + return 0; } static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, @@ -539,8 +597,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; - void *image, *image_end; - u32 i; + u32 i, trampoline_start, image_off = 0; + void *cur_image = NULL, *image = NULL; if (flags) return -EINVAL; @@ -578,8 +636,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; - image = st_map->image; - image_end = st_map->image + PAGE_SIZE; module_type = btf_type_by_id(btf_vmlinux, st_ops_ids[IDX_MODULE_ID]); for_each_member(i, t, member) { @@ -658,15 +714,24 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, &bpf_struct_ops_link_lops, prog); st_map->links[i] = &link->link; + trampoline_start = image_off; err = bpf_struct_ops_prepare_trampoline(tlinks, link, - &st_ops->func_models[i], - *(void **)(st_ops->cfi_stubs + moff), - image, image_end); + &st_ops->func_models[i], + *(void **)(st_ops->cfi_stubs + moff), + &image, &image_off, + st_map->image_pages_cnt < MAX_TRAMP_IMAGE_PAGES); + if (err) + goto reset_unlock; + + if (cur_image != image) { + st_map->image_pages[st_map->image_pages_cnt++] = image; + cur_image = image; + trampoline_start = 0; + } if (err < 0) goto reset_unlock; - *(void **)(kdata + moff) = image + cfi_get_offset(); - image += err; + *(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset(); /* put prog_id to udata */ *(unsigned long *)(udata + moff) = prog->aux->id; @@ -677,10 +742,11 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } + for (i = 0; i < st_map->image_pages_cnt; i++) + arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); if (st_map->map.map_flags & BPF_F_LINK) { err = 0; - arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); /* Let bpf_link handle registration & unregistration. * * Pair with smp_load_acquire() during lookup_elem(). @@ -689,7 +755,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto unlock; } - arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); err = st_ops->reg(kdata); if (likely(!err)) { /* This refcnt increment on the map here after @@ -712,9 +777,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE); reset_unlock: + bpf_struct_ops_map_free_image(st_map); bpf_struct_ops_map_put_progs(st_map); memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); @@ -781,10 +846,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) if (st_map->links) bpf_struct_ops_map_put_progs(st_map); bpf_map_area_free(st_map->links); - if (st_map->image) { - arch_free_bpf_trampoline(st_map->image, PAGE_SIZE); - bpf_jit_uncharge_modmem(PAGE_SIZE); - } + bpf_struct_ops_map_free_image(st_map); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); } @@ -894,20 +956,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) st_map->st_ops_desc = st_ops_desc; map = &st_map->map; - ret = bpf_jit_charge_modmem(PAGE_SIZE); - if (ret) - goto errout_free; - - st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); - if (!st_map->image) { - /* __bpf_struct_ops_map_free() uses st_map->image as flag - * for "charged or not". In this case, we need to unchange - * here. - */ - bpf_jit_uncharge_modmem(PAGE_SIZE); - ret = -ENOMEM; - goto errout_free; - } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); st_map->links_cnt = btf_type_vlen(t); st_map->links = diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 02de71719aed..1b5f812e6972 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -91,6 +91,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, struct bpf_tramp_link *link = NULL; void *image = NULL; unsigned int op_idx; + u32 image_off = 0; int prog_ret; s32 type_id; int err; @@ -114,12 +115,6 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, goto out; } - image = arch_alloc_bpf_trampoline(PAGE_SIZE); - if (!image) { - err = -ENOMEM; - goto out; - } - link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; @@ -133,7 +128,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[op_idx], &dummy_ops_test_ret_function, - image, image + PAGE_SIZE); + &image, &image_off, + true); if (err < 0) goto out; @@ -147,7 +143,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = -EFAULT; out: kfree(args); - arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_struct_ops_image_free(image); if (link) bpf_link_put(&link->link); kfree(tlinks); -- cgit v1.2.3 From 345a6e2631c1267221b684e110bba03e4c26ece0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 Mar 2024 17:19:45 +0000 Subject: tcp: align tcp_sock_write_rx group Stephen Rothwell and kernel test robot reported that some arches (parisc, hexagon) and/or compilers would not like blamed commit. Lets make sure tcp_sock_write_rx group does not start with a hole. While we are at it, correct tcp_sock_write_tx CACHELINE_ASSERT_GROUP_SIZE() since after the blamed commit, we went to 105 bytes. Fixes: 99123622050f ("tcp: remove some holes in struct tcp_sock") Reported-by: Stephen Rothwell Reported-by: kernel test robot Link: https://lore.kernel.org/netdev/20240301121108.5d39e4f9@canb.auug.org.au/ Closes: https://lore.kernel.org/oe-kbuild-all/202403011451.csPYOS3C-lkp@intel.com/ Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Tested-by: Simon Horman # build-tested Link: https://lore.kernel.org/r/20240301171945.2958176-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 988a30ef6bfe..55399ee2a57e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -304,7 +304,7 @@ struct tcp_sock { __cacheline_group_end(tcp_sock_write_txrx); /* RX read-write hotpath cache lines */ - __cacheline_group_begin(tcp_sock_write_rx); + __cacheline_group_begin(tcp_sock_write_rx) __aligned(8); u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived * sum(delta(rcv_nxt)), or how many bytes diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82dc42f57c6..7e1b848398d0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4651,7 +4651,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); -- cgit v1.2.3 From 411c5f36805c02c7c412f1ad6bfa4459a1148011 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:08 +0800 Subject: mm/page_alloc: modify page_frag_alloc_align() to accept align as an argument napi_alloc_frag_align() and netdev_alloc_frag_align() accept align as an argument, and they are thin wrappers around the __napi_alloc_frag_align() and __netdev_alloc_frag_align() APIs doing the alignment checking and align mask conversion, in order to call page_frag_alloc_align() directly. The intention here is to keep the alignment checking and the alignmask conversion in in-line wrapper to avoid those kind of operations during execution time since it can usually be handled during compile time. We are going to use page_frag_alloc_align() in vhost_net.c, it need the same kind of alignment checking and alignmask conversion, so split up page_frag_alloc_align into an inline wrapper doing the above operation, and add __page_frag_alloc_align() which is passed with the align mask the original function expected as suggested by Alexander. Signed-off-by: Yunsheng Lin CC: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- include/linux/gfp.h | 15 +++++++++++---- mm/page_alloc.c | 8 ++++---- net/core/skbuff.c | 9 ++++++--- 3 files changed, 21 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index de292a007138..28aea17fa59b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -312,14 +312,21 @@ extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); -extern void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} static inline void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask) { - return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); } extern void page_frag_free(void *addr); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 150d4f23b010..c0f7e67c4250 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4708,9 +4708,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) } EXPORT_SYMBOL(__page_frag_cache_drain); -void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) { unsigned int size = PAGE_SIZE; struct page *page; @@ -4779,7 +4779,7 @@ refill: return nc->va + offset; } -EXPORT_SYMBOL(page_frag_alloc_align); +EXPORT_SYMBOL(__page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1f918e602bc4..43d7fc150acc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -315,7 +315,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); - return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); @@ -327,13 +328,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); - data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + align_mask); } else { struct napi_alloc_cache *nc; local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache); - data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); local_bh_enable(); } return data; -- cgit v1.2.3 From a0727489ac22d6fbd2e390d38a51193bba61da83 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:10 +0800 Subject: net: introduce page_frag_cache_drain() When draining a page_frag_cache, most user are doing the similar steps, so introduce an API to avoid code duplication. Signed-off-by: Yunsheng Lin Acked-by: Jason Wang Reviewed-by: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/google/gve/gve_main.c | 11 ++--------- drivers/net/ethernet/mediatek/mtk_wed_wo.c | 17 ++--------------- drivers/nvme/host/tcp.c | 7 +------ drivers/nvme/target/tcp.c | 4 +--- include/linux/gfp.h | 1 + mm/page_alloc.c | 10 ++++++++++ 6 files changed, 17 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 7b89b66adb53..166bd827a6d7 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1276,17 +1276,10 @@ static void gve_unreg_xdp_info(struct gve_priv *priv) static void gve_drain_page_cache(struct gve_priv *priv) { - struct page_frag_cache *nc; int i; - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - nc = &priv->rx[i].page_cache; - if (nc->va) { - __page_frag_cache_drain(virt_to_page(nc->va), - nc->pagecnt_bias); - nc->va = NULL; - } - } + for (i = 0; i < priv->rx_cfg.num_queues; i++) + page_frag_cache_drain(&priv->rx[i].page_cache); } static void gve_qpls_get_curr_alloc_cfg(struct gve_priv *priv, diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index d58b07e7e123..7063c78bd35f 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -286,7 +286,6 @@ mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) static void mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; int i; for (i = 0; i < q->n_desc; i++) { @@ -301,19 +300,12 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) entry->buf = NULL; } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; - for (;;) { void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); @@ -323,12 +315,7 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) skb_free_frag(buf); } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index a6d596e05602..3692b56cb58d 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1344,7 +1344,6 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { - struct page *page; struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; unsigned int noreclaim_flag; @@ -1355,11 +1354,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) if (queue->hdr_digest || queue->data_digest) nvme_tcp_free_crypto(queue); - if (queue->pf_cache.va) { - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); - queue->pf_cache.va = NULL; - } + page_frag_cache_drain(&queue->pf_cache); noreclaim_flag = memalloc_noreclaim_save(); /* ->sock will be released by fput() */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index c8655fc5aa5b..2aa5762e9f50 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1591,7 +1591,6 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) static void nvmet_tcp_release_queue_work(struct work_struct *w) { - struct page *page; struct nvmet_tcp_queue *queue = container_of(w, struct nvmet_tcp_queue, release_work); @@ -1615,8 +1614,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) if (queue->hdr_digest || queue->data_digest) nvmet_tcp_free_crypto(queue); ida_free(&nvmet_tcp_queue_ida, queue->idx); - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); + page_frag_cache_drain(&queue->pf_cache); kfree(queue); } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 28aea17fa59b..6cef1c241180 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -311,6 +311,7 @@ extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; +void page_frag_cache_drain(struct page_frag_cache *nc); extern void __page_frag_cache_drain(struct page *page, unsigned int count); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 636145c29f70..06aa1ebbd21c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4699,6 +4699,16 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, return page; } +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); -- cgit v1.2.3 From 885c36e59f46375c138de18ff1692f18eff67b7f Mon Sep 17 00:00:00 2001 From: Abhishek Chauhan Date: Fri, 1 Mar 2024 12:13:48 -0800 Subject: net: Re-use and set mono_delivery_time bit for userspace tstamp packets Bridge driver today has no support to forward the userspace timestamp packets and ends up resetting the timestamp. ETF qdisc checks the packet coming from userspace and encounters to be 0 thereby dropping time sensitive packets. These changes will allow userspace timestamps packets to be forwarded from the bridge to NIC drivers. Setting the same bit (mono_delivery_time) to avoid dropping of userspace tstamp packets in the forwarding path. Existing functionality of mono_delivery_time remains unaltered here, instead just extended with userspace tstamp support for bridge forwarding path. Signed-off-by: Abhishek Chauhan Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20240301201348.2815102-1-quic_abchauha@quicinc.com Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 6 +++--- net/ipv4/ip_output.c | 1 + net/ipv4/raw.c | 1 + net/ipv6/ip6_output.c | 2 +- net/ipv6/raw.c | 2 +- net/packet/af_packet.c | 4 +++- 6 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d577e0bee18d..3013355b63f5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -822,9 +822,9 @@ typedef unsigned char *sk_buff_data_t; * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * delivery_time in mono clock base (i.e., EDT) or a clock base chosen + * by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at + * ingress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1fe794967211..33f93dc730a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1458,6 +1458,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a82fd102df05..494a6284bd7e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -353,6 +353,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b9dd3a66e423..02eeca5492cd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 76e6eb3b643d..779274055abf 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -615,7 +615,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9bbc2686690..0db31ca4982d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ retry: skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2586,6 +2586,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3064,6 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; + skb->mono_delivery_time = !!skb->tstamp; if (unlikely(extra_len == 4)) skb->no_fcs = 1; -- cgit v1.2.3 From e3b6876ab85061e7de198f023a0c2bfc7478b420 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 2 Mar 2024 20:53:01 +0100 Subject: net: phy: Add phydev->enable_tx_lpi to simplify adjust link callbacks MAC drivers which support EEE need to know the results of the EEE auto-neg in order to program the hardware to perform EEE or not. The oddly named phy_init_eee() can be used to determine this, it returns 0 if EEE should be used, or a negative error code, e.g. -EOPPROTONOTSUPPORT if the PHY does not support EEE or negotiate resulted in it not being used. However, many MAC drivers get this wrong. Add phydev->enable_tx_lpi which indicates the result of the autoneg for EEE, including if EEE is administratively disabled with ethtool. The MAC driver can then access this in the same way as link speed and duplex in the adjust link callback. If enable_tx_lpi is true, the MAC should send low power indications and does not need to consider anything else with respect to EEE. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20240302195306.3207716-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy.c | 7 +++++++ include/linux/phy.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 14224e06d69f..2bc0a7d51c63 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -983,9 +983,16 @@ static int phy_check_link_status(struct phy_device *phydev) if (phydev->link && phydev->state != PHY_RUNNING) { phy_check_downshift(phydev); phydev->state = PHY_RUNNING; + err = genphy_c45_eee_is_active(phydev, + NULL, NULL, NULL); + if (err < 0) + phydev->enable_tx_lpi = false; + else + phydev->enable_tx_lpi = !!err; phy_link_up(phydev); } else if (!phydev->link && phydev->state != PHY_NOLINK) { phydev->state = PHY_NOLINK; + phydev->enable_tx_lpi = false; phy_link_down(phydev); } diff --git a/include/linux/phy.h b/include/linux/phy.h index e3ab2c347a59..a880f6d7170e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -594,6 +594,7 @@ struct macsec_ops; * @supported_eee: supported PHY EEE linkmodes * @advertising_eee: Currently advertised EEE linkmodes * @eee_enabled: Flag indicating whether the EEE feature is enabled + * @enable_tx_lpi: When True, MAC should transmit LPI to PHY * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited @@ -713,6 +714,7 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; + bool enable_tx_lpi; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; -- cgit v1.2.3 From fe0d4fd9285e5013b4bafbd3338847235b805a1c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 2 Mar 2024 20:53:02 +0100 Subject: net: phy: Keep track of EEE configuration Have phylib keep track of the EEE configuration. This simplifies the MAC drivers, in that they don't need to store it. Future patches to phylib will also make use of this information to further simplify the MAC drivers. Reviewed-by: Russell King (Oracle) Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20240302195306.3207716-4-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy.c | 7 +++++-- include/linux/phy.h | 3 +++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 2bc0a7d51c63..95c4ef5d4e97 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1640,8 +1640,8 @@ EXPORT_SYMBOL(phy_get_eee_err); * @phydev: target phy_device struct * @data: ethtool_keee data * - * Description: it reportes the Supported/Advertisement/LP Advertisement - * capabilities. + * Description: reports the Supported/Advertisement/LP Advertisement + * capabilities, etc. */ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) { @@ -1652,6 +1652,7 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) mutex_lock(&phydev->lock); ret = genphy_c45_ethtool_get_eee(phydev, data); + eeecfg_to_eee(data, &phydev->eee_cfg); mutex_unlock(&phydev->lock); return ret; @@ -1674,6 +1675,8 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data) mutex_lock(&phydev->lock); ret = genphy_c45_ethtool_set_eee(phydev, data); + if (!ret) + eee_to_eeecfg(&phydev->eee_cfg, data); mutex_unlock(&phydev->lock); return ret; diff --git a/include/linux/phy.h b/include/linux/phy.h index a880f6d7170e..695e366bd75c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -30,6 +30,7 @@ #include #include +#include #define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ @@ -595,6 +596,7 @@ struct macsec_ops; * @advertising_eee: Currently advertised EEE linkmodes * @eee_enabled: Flag indicating whether the EEE feature is enabled * @enable_tx_lpi: When True, MAC should transmit LPI to PHY + * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited @@ -715,6 +717,7 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; bool enable_tx_lpi; + struct eee_config eee_cfg; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; -- cgit v1.2.3 From 49168d1980e220cf3d1b761e1eafac62041cb94d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 2 Mar 2024 20:53:04 +0100 Subject: net: phy: Add phy_support_eee() indicating MAC support EEE In order for EEE to operate, both the MAC and the PHY need to support it, similar to how pause works. With some exception - a number of PHYs have SmartEEE or AutoGrEEEn support in order to provide some EEE-like power savings with non-EEE capable MACs. Copy the pause concept and add the call phy_support_eee() which the MAC makes after connecting the PHY to indicate it supports EEE. phylib will then advertise EEE when auto-neg is performed. Signed-off-by: Andrew Lunn Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20240302195306.3207716-6-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 28 ++++++++++++++++++++++++++++ include/linux/phy.h | 3 ++- 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2eefee970851..72452e6a478c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2910,6 +2910,34 @@ void phy_advertise_eee_all(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_advertise_eee_all); +/** + * phy_support_eee - Set initial EEE policy configuration + * @phydev: Target phy_device struct + * + * This function configures the initial policy for Energy Efficient Ethernet + * (EEE) on the specified PHY device, influencing that EEE capabilities are + * advertised before the link is established. It should be called during PHY + * registration by the MAC driver and/or the PHY driver (for SmartEEE PHYs) + * if MAC supports LPI or PHY is capable to compensate missing LPI functionality + * of the MAC. + * + * The function sets default EEE policy parameters, including preparing the PHY + * to advertise EEE capabilities based on hardware support. + * + * It also sets the expected configuration for Low Power Idle (LPI) in the MAC + * driver. If the PHY framework determines that both local and remote + * advertisements support EEE, and the negotiated link mode is compatible with + * EEE, it will set enable_tx_lpi = true. The MAC driver is expected to act on + * this setting by enabling the LPI timer if enable_tx_lpi is set. + */ +void phy_support_eee(struct phy_device *phydev) +{ + linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + phydev->eee_cfg.tx_lpi_enabled = true; + phydev->eee_cfg.eee_enabled = true; +} +EXPORT_SYMBOL(phy_support_eee); + /** * phy_support_sym_pause - Enable support of symmetrical pause * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index 695e366bd75c..3f68b8239bb1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -706,7 +706,7 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - /* used for eee validation */ + /* used for eee validation and configuration*/ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); bool eee_enabled; @@ -1973,6 +1973,7 @@ void phy_advertise_supported(struct phy_device *phydev); void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_support_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); -- cgit v1.2.3 From e6f798225a31485e47a6e4f6aa07ee9fdf80c2cb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 4 Mar 2024 19:05:16 -0800 Subject: mm: Introduce VM_SPARSE kind and vm_area_[un]map_pages(). vmap/vmalloc APIs are used to map a set of pages into contiguous kernel virtual space. get_vm_area() with appropriate flag is used to request an area of kernel address range. It's used for vmalloc, vmap, ioremap, xen use cases. - vmalloc use case dominates the usage. Such vm areas have VM_ALLOC flag. - the areas created by vmap() function should be tagged with VM_MAP. - ioremap areas are tagged with VM_IOREMAP. BPF would like to extend the vmap API to implement a lazily-populated sparse, yet contiguous kernel virtual space. Introduce VM_SPARSE flag and vm_area_map_pages(area, start_addr, count, pages) API to map a set of pages within a given area. It has the same sanity checks as vmap() does. It also checks that get_vm_area() was created with VM_SPARSE flag which identifies such areas in /proc/vmallocinfo and returns zero pages on read through /proc/kcore. The next commits will introduce bpf_arena which is a sparsely populated shared memory region between bpf program and user space process. It will map privately-managed pages into a sparse vm area with the following steps: // request virtual memory region during bpf prog verification area = get_vm_area(area_size, VM_SPARSE); // on demand vm_area_map_pages(area, kaddr, kend, pages); vm_area_unmap_pages(area, kaddr, kend); // after bpf program is detached and unloaded free_vm_area(area); Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Reviewed-by: Christoph Hellwig Reviewed-by: Pasha Tatashin Link: https://lore.kernel.org/bpf/20240305030516.41519-3-alexei.starovoitov@gmail.com --- include/linux/vmalloc.h | 5 +++++ mm/vmalloc.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 62 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index c720be70c8dd..0f72c85a377b 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -35,6 +35,7 @@ struct iov_iter; /* in uio.h */ #else #define VM_DEFER_KMEMLEAK 0 #endif +#define VM_SPARSE 0x00001000 /* sparse vm_area. not all pages are present. */ /* bits [20..32] reserved for arch specific ioremap internals */ @@ -232,6 +233,10 @@ static inline bool is_vm_area_hugepages(const void *addr) } #ifdef CONFIG_MMU +int vm_area_map_pages(struct vm_struct *area, unsigned long start, + unsigned long end, struct page **pages); +void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, + unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f42f98a127d5..e5b8c70950bc 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -648,6 +648,58 @@ static int vmap_pages_range(unsigned long addr, unsigned long end, return err; } +static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, + unsigned long end) +{ + might_sleep(); + if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) + return -EINVAL; + if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) + return -EINVAL; + if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) + return -EINVAL; + if ((end - start) >> PAGE_SHIFT > totalram_pages()) + return -E2BIG; + if (start < (unsigned long)area->addr || + (void *)end > area->addr + get_vm_area_size(area)) + return -ERANGE; + return 0; +} + +/** + * vm_area_map_pages - map pages inside given sparse vm_area + * @area: vm_area + * @start: start address inside vm_area + * @end: end address inside vm_area + * @pages: pages to map (always PAGE_SIZE pages) + */ +int vm_area_map_pages(struct vm_struct *area, unsigned long start, + unsigned long end, struct page **pages) +{ + int err; + + err = check_sparse_vm_area(area, start, end); + if (err) + return err; + + return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); +} + +/** + * vm_area_unmap_pages - unmap pages inside given sparse vm_area + * @area: vm_area + * @start: start address inside vm_area + * @end: end address inside vm_area + */ +void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, + unsigned long end) +{ + if (check_sparse_vm_area(area, start, end)) + return; + + vunmap_range(start, end); +} + int is_vmalloc_or_module_addr(const void *x) { /* @@ -3822,9 +3874,9 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); - else if (!(vm && (vm->flags & VM_IOREMAP))) + else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) copied = aligned_vread_iter(iter, addr, n); - else /* IOREMAP area is treated as memory hole */ + else /* IOREMAP | SPARSE area is treated as memory hole */ copied = zero_iter(iter, n); addr += copied; @@ -4415,6 +4467,9 @@ static int s_show(struct seq_file *m, void *p) if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); + if (v->flags & VM_SPARSE) + seq_puts(m, " sparse"); + if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); -- cgit v1.2.3 From 011832b97b311bb9e3c27945bc0d1089a14209c9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 5 Mar 2024 19:19:26 -0800 Subject: bpf: Introduce may_goto instruction Introduce may_goto instruction that from the verifier pov is similar to open coded iterators bpf_for()/bpf_repeat() and bpf_loop() helper, but it doesn't iterate any objects. In assembly 'may_goto' is a nop most of the time until bpf runtime has to terminate the program for whatever reason. In the current implementation may_goto has a hidden counter, but other mechanisms can be used. For programs written in C the later patch introduces 'cond_break' macro that combines 'may_goto' with 'break' statement and has similar semantics: cond_break is a nop until bpf runtime has to break out of this loop. It can be used in any normal "for" or "while" loop, like for (i = zero; i < cnt; cond_break, i++) { The verifier recognizes that may_goto is used in the program, reserves additional 8 bytes of stack, initializes them in subprog prologue, and replaces may_goto instruction with: aux_reg = *(u64 *)(fp - 40) if aux_reg == 0 goto pc+off aux_reg -= 1 *(u64 *)(fp - 40) = aux_reg may_goto instruction can be used by LLVM to implement __builtin_memcpy, __builtin_strcmp. may_goto is not a full substitute for bpf_for() macro. bpf_for() doesn't have induction variable that verifiers sees, so 'i' in bpf_for(i, 0, 100) is seen as imprecise and bounded. But when the code is written as: for (i = 0; i < 100; cond_break, i++) the verifier see 'i' as precise constant zero, hence cond_break (aka may_goto) doesn't help to converge the loop. A static or global variable can be used as a workaround: static int zero = 0; for (i = zero; i < 100; cond_break, i++) // works! may_goto works well with arena pointers that don't need to be bounds checked on access. Load/store from arena returns imprecise unbounded scalar and loops with may_goto pass the verifier. Reserve new opcode BPF_JMP | BPF_JCOND for may_goto insn. JCOND stands for conditional pseudo jump. Since goto_or_nop insn was proposed, it may use the same opcode. may_goto vs goto_or_nop can be distinguished by src_reg: code = BPF_JMP | BPF_JCOND src_reg = 0 - may_goto src_reg = 1 - goto_or_nop Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: Eduard Zingerman Acked-by: John Fastabend Tested-by: John Fastabend Link: https://lore.kernel.org/bpf/20240306031929.42666-2-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 2 + include/uapi/linux/bpf.h | 5 ++ kernel/bpf/core.c | 1 + kernel/bpf/disasm.c | 4 + kernel/bpf/verifier.c | 163 +++++++++++++++++++++++++++++++++-------- tools/include/uapi/linux/bpf.h | 5 ++ 6 files changed, 150 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 84365e6dd85d..4b0f6600e499 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -449,6 +449,7 @@ struct bpf_verifier_state { u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; + u32 may_goto_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -619,6 +620,7 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ + u16 stack_extra; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a241f407c234..85ec7fc799d7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -42,6 +42,7 @@ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSLT 0xc0 /* SLT is signed, '<' */ #define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -50,6 +51,10 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + /* Register numbers */ enum { BPF_REG_0 = 0, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 71c459a51d9e..9ee4536d0a09 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1675,6 +1675,7 @@ bool bpf_opcode_in_insntable(u8 code) [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, + [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 49940c26a227..82b2dbdd048f 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -322,6 +322,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_JCOND) && + insn->src_reg == BPF_MAY_GOTO) { + verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", + insn->code, insn->off); } else if (insn->code == (BPF_JMP32 | BPF_JA)) { verbose(cbs->private_data, "(%02x) gotol pc%+d\n", insn->code, insn->imm); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4dd84e13bbfe..8030b50d3b45 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -533,6 +533,16 @@ static bool is_async_callback_calling_insn(struct bpf_insn *insn) return bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm); } +static bool is_may_goto_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; +} + +static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) +{ + return is_may_goto_insn(&env->prog->insnsi[insn_idx]); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1429,6 +1439,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->dfs_depth = src->dfs_depth; dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; + dst_state->may_goto_depth = src->may_goto_depth; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -14871,11 +14882,36 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, int err; /* Only conditional jumps are expected to reach here. */ - if (opcode == BPF_JA || opcode > BPF_JSLE) { + if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } + if (opcode == BPF_JCOND) { + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; + int idx = *insn_idx; + + if (insn->code != (BPF_JMP | BPF_JCOND) || + insn->src_reg != BPF_MAY_GOTO || + insn->dst_reg || insn->imm || insn->off == 0) { + verbose(env, "invalid may_goto off %d imm %d\n", + insn->off, insn->imm); + return -EINVAL; + } + prev_st = find_prev_entry(env, cur_st->parent, idx); + + /* branch out 'fallthrough' insn as a new state to explore */ + queued_st = push_stack(env, idx + 1, idx, false); + if (!queued_st) + return -ENOMEM; + + queued_st->may_goto_depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); + *insn_idx += insn->off; + return 0; + } + /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) @@ -15659,6 +15695,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) default: /* conditional jump with two edges */ mark_prune_point(env, t); + if (is_may_goto_insn(insn)) + mark_force_checkpoint(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) @@ -17135,6 +17173,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } goto skip_inf_loop_check; } + if (is_may_goto_insn_at(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, true)) { + update_loop_entry(cur, &sl->state); + goto hit; + } + goto skip_inf_loop_check; + } if (calls_callback(env, insn_idx)) { if (states_equal(env, &sl->state, cur, true)) goto hit; @@ -17144,6 +17189,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, true) && !iter_active_depths_differ(&sl->state, cur) && + sl->state.may_goto_depth == cur->may_goto_depth && sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); @@ -19408,7 +19454,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, ret, cnt, delta = 0; + int i, ret, cnt, delta = 0, cur_subprog = 0; + struct bpf_subprog_info *subprogs = env->subprog_info; + u16 stack_depth = subprogs[cur_subprog].stack_depth; + u16 stack_depth_extra = 0; if (env->seen_exception && !env->exception_callback_subprog) { struct bpf_insn patch[] = { @@ -19428,7 +19477,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) mark_subprog_exc_cb(env, env->exception_callback_subprog); } - for (i = 0; i < insn_cnt; i++, insn++) { + for (i = 0; i < insn_cnt;) { /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || @@ -19467,7 +19516,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ @@ -19487,7 +19536,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ @@ -19502,7 +19551,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) - continue; + goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == @@ -19540,19 +19589,39 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; + } + + if (is_may_goto_insn(insn)) { + int stack_off = -stack_depth - 8; + + stack_depth_extra = 8; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); + cnt = 4; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; } if (insn->code != (BPF_JMP | BPF_CALL)) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) - continue; + goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) @@ -19561,7 +19630,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_get_route_realm) @@ -19609,11 +19678,11 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } insn->imm = ret + 1; - continue; + goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) - continue; + goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: @@ -19642,7 +19711,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { @@ -19754,7 +19823,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, @@ -19785,31 +19854,31 @@ patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); - continue; + goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); - continue; + goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); - continue; + goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); - continue; + goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); - continue; + goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); - continue; + goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); - continue; + goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); - continue; + goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); - continue; + goto next_insn; } goto patch_call_imm; @@ -19837,7 +19906,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_arg inline. */ @@ -19862,7 +19931,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ret inline. */ @@ -19890,7 +19959,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement get_func_arg_cnt inline. */ @@ -19905,7 +19974,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ip inline. */ @@ -19920,7 +19989,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_kptr_xchg inline */ @@ -19938,7 +20007,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); @@ -19952,6 +20021,40 @@ patch_call_imm: return -EFAULT; } insn->imm = fn->func - __bpf_call_base; +next_insn: + if (subprogs[cur_subprog + 1].start == i + delta + 1) { + subprogs[cur_subprog].stack_depth += stack_depth_extra; + subprogs[cur_subprog].stack_extra = stack_depth_extra; + cur_subprog++; + stack_depth = subprogs[cur_subprog].stack_depth; + stack_depth_extra = 0; + } + i++; + insn++; + } + + env->prog->aux->stack_depth = subprogs[0].stack_depth; + for (i = 0; i < env->subprog_cnt; i++) { + int subprog_start = subprogs[i].start; + int stack_slots = subprogs[i].stack_extra / 8; + + if (!stack_slots) + continue; + if (stack_slots > 1) { + verbose(env, "verifier bug: stack_slots supports may_goto only\n"); + return -EFAULT; + } + + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, + -subprogs[i].stack_depth, BPF_MAX_LOOPS); + /* Copy first actual insn to preserve it */ + insn_buf[1] = env->prog->insnsi[subprog_start]; + + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); + if (!new_prog) + return -ENOMEM; + env->prog = prog = new_prog; } /* Since poke tab is now finalized, publish aux to tracker. */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a241f407c234..85ec7fc799d7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -42,6 +42,7 @@ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSLT 0xc0 /* SLT is signed, '<' */ #define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -50,6 +51,10 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From a0873a5d542559698edfd4c8fc6e6636d338eea2 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 14 Feb 2024 19:08:00 -0800 Subject: net/mlx5: Add MPIR bit in mcam_access_reg Add a cap bit in mcam_access_reg to check for MPIR support. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 628a3aa7a7e0..2756bdb654b4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10253,7 +10253,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcqi[0x1]; u8 mcqs[0x1]; - u8 regs_95_to_87[0x9]; + u8 regs_95_to_90[0x6]; + u8 mpir[0x1]; + u8 regs_88_to_87[0x2]; u8 mpegc[0x1]; u8 mtutc[0x1]; u8 regs_84_to_68[0x11]; -- cgit v1.2.3 From ed29705e4ed1d5c1b2184fecc4684bd56c5d24ee Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 14 Feb 2024 19:08:13 -0800 Subject: net/mlx5: Enable SD feature Have an actual mlx5_sd instance in the core device, and fix the getter accordingly. This allows SD stuff to flow, the feature becomes supported only here. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 3 ++- include/linux/mlx5/driver.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 0810b92b48d0..37d5f445598c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -59,10 +59,11 @@ struct mlx5_sd; static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev) { - return NULL; + return dev->sd; } static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd) { + dev->sd = sd; } #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41f03b352401..bf9324a31ae9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -823,6 +823,7 @@ struct mlx5_core_dev { struct blocking_notifier_head macsec_nh; #endif u64 num_ipsec_offloads; + struct mlx5_sd *sd; }; struct mlx5_db { -- cgit v1.2.3 From 68ac1e46425c54653ddb5f559bc37abe19071024 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 1 Mar 2024 17:43:08 +0100 Subject: net: phylink: clean the pcs_get_state documentation commit 4d72c3bb60dd ("net: phylink: strip out pre-March 2020 legacy code") dropped the mac_pcs_get_state ops in phylink_mac_ops in favor of dedicated PCS operation pcs_get_state. However, the documentation for the pcs_get_state ops was incorrectly converted and now self-references. Drop the extra comment. Signed-off-by: Maxime Chevallier Signed-off-by: Paolo Abeni --- include/linux/phylink.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 6ba411732a0d..9a57deefcb07 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -480,9 +480,6 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. - * - * When present, this overrides pcs_get_state() in &struct - * phylink_pcs_ops. */ void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); -- cgit v1.2.3 From cf2c2e4a3d910270903d50462aaa75140cdb2c96 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Mar 2024 19:12:25 -0800 Subject: bpf: Plumb get_unmapped_area() callback into bpf_map_ops Subsequent patches introduce bpf_arena that imposes special alignment requirements on address selection. Acked-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/r/20240307031228.42896-4-alexei.starovoitov@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 3 +++ kernel/bpf/syscall.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 785660810e6a..95e07673cdc1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -139,6 +139,9 @@ struct bpf_map_ops { int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b2750b79ac80..f63f4da4db5e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -937,6 +937,21 @@ static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) return EPOLLERR; } +static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + + if (map->ops->map_get_unmapped_area) + return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); +#ifdef CONFIG_MMU + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +#else + return addr; +#endif +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -946,6 +961,7 @@ const struct file_operations bpf_map_fops = { .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, + .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) -- cgit v1.2.3 From 2658b5a8a4eee5fad378d0bde2f221deacbc58f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:14 +0000 Subject: net: introduce struct net_hotdata Instead of spreading networking critical fields all over the places, add a custom net_hotdata structure so that we can precisely control its layout. In this first patch, move : - gro_normal_batch used in rx (GRO stack) - offload_base used in rx and tx (GRO and TSO stacks) Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - include/net/gro.h | 5 ++--- include/net/hotdata.h | 15 +++++++++++++++ net/core/Makefile | 1 + net/core/gro.c | 15 ++++++--------- net/core/gso.c | 4 ++-- net/core/hotdata.c | 9 +++++++++ net/core/sysctl_net_core.c | 3 ++- 8 files changed, 37 insertions(+), 16 deletions(-) create mode 100644 include/net/hotdata.h create mode 100644 net/core/hotdata.c (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2767467138a0..6643452af543 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4796,7 +4796,6 @@ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); extern int netdev_max_backlog; extern int dev_rx_weight; extern int dev_tx_weight; -extern int gro_normal_batch; enum { NESTED_SYNC_IMM_BIT, diff --git a/include/net/gro.h b/include/net/gro.h index 2b58671a6549..d6fc8fbd3730 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -9,6 +9,7 @@ #include #include #include +#include struct napi_gro_cb { union { @@ -446,7 +447,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, { list_add_tail(&skb->list, &napi->rx_list); napi->rx_count += segs; - if (napi->rx_count >= READ_ONCE(gro_normal_batch)) + if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) gro_normal_list(napi); } @@ -493,6 +494,4 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * #endif } -extern struct list_head offload_base; - #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/hotdata.h b/include/net/hotdata.h new file mode 100644 index 000000000000..6ed32e4e34aa --- /dev/null +++ b/include/net/hotdata.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_HOTDATA_H +#define _NET_HOTDATA_H + +#include + +/* Read mostly data used in network fast paths. */ +struct net_hotdata { + struct list_head offload_base; + int gro_normal_batch; +}; + +extern struct net_hotdata net_hotdata; + +#endif /* _NET_HOTDATA_H */ diff --git a/net/core/Makefile b/net/core/Makefile index 821aec06abf1..6e6548011fae 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,6 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o +obj-y += hotdata.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/gro.c b/net/core/gro.c index 6a0edbd826a1..ee30d4f0c038 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -10,9 +10,6 @@ #define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(offload_lock); -struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /** * dev_add_offload - register offload handlers @@ -31,7 +28,7 @@ void dev_add_offload(struct packet_offload *po) struct packet_offload *elem; spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { + list_for_each_entry(elem, &net_hotdata.offload_base, list) { if (po->priority < elem->priority) break; } @@ -55,7 +52,7 @@ EXPORT_SYMBOL(dev_add_offload); */ static void __dev_remove_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *po1; spin_lock(&offload_lock); @@ -235,9 +232,9 @@ done: static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; int err = -ENOENT; BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); @@ -444,7 +441,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; @@ -550,7 +547,7 @@ normal: struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -564,7 +561,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type); struct packet_offload *gro_find_complete_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { diff --git a/net/core/gso.c b/net/core/gso.c index 9e1803bfc9c6..bcd156372f4d 100644 --- a/net/core/gso.c +++ b/net/core/gso.c @@ -17,7 +17,7 @@ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, struct packet_offload *ptype; rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; @@ -48,7 +48,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, __skb_pull(skb, vlan_depth); rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; diff --git a/net/core/hotdata.c b/net/core/hotdata.c new file mode 100644 index 000000000000..abb8ad19d59a --- /dev/null +++ b/net/core/hotdata.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include +#include +#include + +struct net_hotdata net_hotdata __cacheline_aligned = { + .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), + .gro_normal_batch = 8, +}; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 986f15e5d6c4..0eb1242eabbe 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "dev.h" @@ -632,7 +633,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "gro_normal_batch", - .data = &gro_normal_batch, + .data = &net_hotdata.gro_normal_batch, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, -- cgit v1.2.3 From 0b91fa4bfb1caedd01cb6eb3b733cbc77c9edb0e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:17 +0000 Subject: net: move ptype_all into net_hotdata ptype_all is used in rx/tx fast paths. Move it to net_hotdata for better cache locality. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - include/net/hotdata.h | 1 + net/core/dev.c | 16 +++++++--------- net/core/hotdata.c | 1 + net/core/net-procfs.c | 7 ++++--- 5 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6643452af543..b18ac8072f18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5306,7 +5306,6 @@ static inline const char *netdev_reg_state(const struct net_device *dev) #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) -extern struct list_head ptype_all __read_mostly; extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; diff --git a/include/net/hotdata.h b/include/net/hotdata.h index 149e56528537..d462cb8f16ba 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -7,6 +7,7 @@ /* Read mostly data used in network fast paths. */ struct net_hotdata { struct list_head offload_base; + struct list_head ptype_all; int gro_normal_batch; int netdev_budget; int netdev_budget_usecs; diff --git a/net/core/dev.c b/net/core/dev.c index f2f44303c035..e1493e558407 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -161,7 +161,6 @@ static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -struct list_head ptype_all __read_mostly; /* Taps */ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, @@ -540,7 +539,7 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) - return pt->dev ? &pt->dev->ptype_all : &ptype_all; + return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; @@ -2226,7 +2225,8 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) */ bool dev_nit_active(struct net_device *dev) { - return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); + return !list_empty(&net_hotdata.ptype_all) || + !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); @@ -2237,10 +2237,9 @@ EXPORT_SYMBOL_GPL(dev_nit_active); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { - struct packet_type *ptype; + struct list_head *ptype_list = &net_hotdata.ptype_all; + struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; - struct packet_type *pt_prev = NULL; - struct list_head *ptype_list = &ptype_all; rcu_read_lock(); again: @@ -2286,7 +2285,7 @@ again: pt_prev = ptype; } - if (ptype_list == &ptype_all) { + if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } @@ -5387,7 +5386,7 @@ another_round: if (pfmemalloc) goto skip_taps; - list_for_each_entry_rcu(ptype, &ptype_all, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -11749,7 +11748,6 @@ static int __init net_dev_init(void) if (netdev_kobject_init()) goto out; - INIT_LIST_HEAD(&ptype_all); for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 087c4c84987d..29fcfe89fd9a 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -7,6 +7,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), + .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all), .gro_normal_batch = 8, .netdev_budget = 300, diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 2e4e96d30ee1..a97eceb84e61 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "dev.h" @@ -183,7 +184,7 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) } } - list_for_each_entry_rcu(pt, &ptype_all, list) { + list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { if (i == pos) return pt; ++i; @@ -231,13 +232,13 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) } } - nxt = ptype_all.next; + nxt = net_hotdata.ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: - if (nxt != &ptype_all) + if (nxt != &net_hotdata.ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; -- cgit v1.2.3 From edbc666cdcbf4a80ada4311c272a2078af87b880 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:18 +0000 Subject: net: move netdev_max_backlog to net_hotdata netdev_max_backlog is used in rx fat path. Move it to net_hodata for better cache locality. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-6-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - include/net/hotdata.h | 1 + net/core/dev.c | 8 +++----- net/core/gro_cells.c | 3 ++- net/core/hotdata.c | 2 ++ net/core/sysctl_net_core.c | 2 +- net/xfrm/espintcp.c | 4 +++- net/xfrm/xfrm_input.c | 3 ++- 8 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b18ac8072f18..c9a671b7bb37 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4793,7 +4793,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); -extern int netdev_max_backlog; extern int dev_rx_weight; extern int dev_tx_weight; diff --git a/include/net/hotdata.h b/include/net/hotdata.h index d462cb8f16ba..dc50b200a94b 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -12,6 +12,7 @@ struct net_hotdata { int netdev_budget; int netdev_budget_usecs; int tstamp_prequeue; + int max_backlog; }; extern struct net_hotdata net_hotdata; diff --git a/net/core/dev.c b/net/core/dev.c index e1493e558407..e23edbaff392 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4404,9 +4404,6 @@ EXPORT_SYMBOL(__dev_direct_xmit); * Receiver routines *************************************************************************/ -int netdev_max_backlog __read_mostly = 1000; -EXPORT_SYMBOL(netdev_max_backlog); - unsigned int sysctl_skb_defer_max __read_mostly = 64; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ @@ -4713,7 +4710,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) + if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4761,7 +4758,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(net_hotdata.max_backlog) && + !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index ed5ec5de47f6..ff8e5b64bf6b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -3,6 +3,7 @@ #include #include #include +#include struct gro_cell { struct sk_buff_head napi_skbs; @@ -26,7 +27,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 29fcfe89fd9a..35ed5a83ecc7 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -15,4 +15,6 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .netdev_budget_usecs = 2 * USEC_PER_SEC / HZ, .tstamp_prequeue = 1, + .max_backlog = 1000, }; +EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index bddd07da0998..8eaeeb289914 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -440,7 +440,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_max_backlog", - .data = &netdev_max_backlog, + .data = &net_hotdata.max_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index d3b3f9e720b3..fe82e2d07300 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -10,6 +10,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include #endif +#include static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, struct sock *sk) @@ -169,7 +170,8 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&ctx->out_queue) >= + READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd4ce21d76d7..161f535c8b94 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "xfrm_inout.h" @@ -764,7 +765,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); -- cgit v1.2.3 From 26722dc74bf08fd79564cbcad1e5f3e2aa3bf9cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:21 +0000 Subject: net: move dev_tx_weight to net_hotdata dev_tx_weight is used in tx fast path. Move it to net_hotdata for better cache locality. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-9-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - include/net/hotdata.h | 1 + net/core/dev.c | 1 - net/core/hotdata.c | 1 + net/core/sysctl_net_core.c | 2 +- net/sched/sch_generic.c | 3 ++- 6 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c9a671b7bb37..ad4b031098ff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4794,7 +4794,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); extern int dev_rx_weight; -extern int dev_tx_weight; enum { NESTED_SYNC_IMM_BIT, diff --git a/include/net/hotdata.h b/include/net/hotdata.h index d86d02f156fc..ffea9cc263e5 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -21,6 +21,7 @@ struct net_hotdata { int netdev_budget_usecs; int tstamp_prequeue; int max_backlog; + int dev_tx_weight; }; extern struct net_hotdata net_hotdata; diff --git a/net/core/dev.c b/net/core/dev.c index e23edbaff392..5d6bd481103f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4409,7 +4409,6 @@ int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; -int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 35ed5a83ecc7..ec8c3b48e8fe 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -16,5 +16,6 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .tstamp_prequeue = 1, .max_backlog = 1000, + .dev_tx_weight = 64, }; EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8eaeeb289914..a30016a8660e 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -302,7 +302,7 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, if (!ret && write) { weight = READ_ONCE(weight_p); WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); - WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9b3e9262040b..ff5336493777 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -409,7 +410,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = READ_ONCE(dev_tx_weight); + int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { -- cgit v1.2.3 From 71c0de9bac9c1dda503322c86be4924f055dc6c9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:22 +0000 Subject: net: move dev_rx_weight to net_hotdata dev_rx_weight is read from process_backlog(). Move it to net_hotdata for better cache locality. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-10-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 -- include/net/hotdata.h | 1 + net/core/dev.c | 3 +-- net/core/hotdata.c | 1 + net/core/sysctl_net_core.c | 2 +- 5 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ad4b031098ff..dd641297e807 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4793,8 +4793,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); -extern int dev_rx_weight; - enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, diff --git a/include/net/hotdata.h b/include/net/hotdata.h index ffea9cc263e5..e6595ed2c3be 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -22,6 +22,7 @@ struct net_hotdata { int tstamp_prequeue; int max_backlog; int dev_tx_weight; + int dev_rx_weight; }; extern struct net_hotdata net_hotdata; diff --git a/net/core/dev.c b/net/core/dev.c index 5d6bd481103f..40ba02e04bcb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4408,7 +4408,6 @@ unsigned int sysctl_skb_defer_max __read_mostly = 64; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ -int dev_rx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -5978,7 +5977,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = READ_ONCE(dev_rx_weight); + napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; diff --git a/net/core/hotdata.c b/net/core/hotdata.c index ec8c3b48e8fe..c8a7a451c18a 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -17,5 +17,6 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .tstamp_prequeue = 1, .max_backlog = 1000, .dev_tx_weight = 64, + .dev_rx_weight = 64, }; EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index a30016a8660e..8a4c698dad9c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -301,7 +301,7 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); - WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); -- cgit v1.2.3 From aa70d2d16f280efe8aa52afc25a33b2ec8d346b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:23 +0000 Subject: net: move skbuff_cache(s) to net_hotdata skbuff_cache, skbuff_fclone_cache and skb_small_head_cache are used in rx/tx fast paths. Move them to net_hotdata for better cache locality. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-11-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 - include/net/hotdata.h | 3 +++ kernel/bpf/cpumap.c | 4 +++- net/bpf/test_run.c | 4 +++- net/core/skbuff.c | 44 ++++++++++++++++++++------------------------ net/core/xdp.c | 5 +++-- 6 files changed, 32 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3013355b63f5..d0508f90bed5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1271,7 +1271,6 @@ static inline void consume_skb(struct sk_buff *skb) void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); -extern struct kmem_cache *skbuff_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, diff --git a/include/net/hotdata.h b/include/net/hotdata.h index e6595ed2c3be..a8f7e5e826fb 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -16,6 +16,9 @@ struct net_hotdata { #endif struct list_head offload_base; struct list_head ptype_all; + struct kmem_cache *skbuff_cache; + struct kmem_cache *skbuff_fclone_cache; + struct kmem_cache *skb_small_head_cache; int gro_normal_batch; int netdev_budget; int netdev_budget_usecs; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ef82ffc90cbe..9ee8da477465 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -326,7 +327,8 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 5535f9adc658..61efeadaff8d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -254,7 +255,8 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, nframes, + (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 43d7fc150acc..766219011aea 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include #include #include +#include #include #include #include @@ -88,15 +89,10 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_cache __ro_after_init; -static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif - -static struct kmem_cache *skb_small_head_cache __ro_after_init; - #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. @@ -349,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -358,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); + kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; } @@ -416,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -467,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -578,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { - obj = kmem_cache_alloc_node(skb_small_head_cache, + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; @@ -586,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node); + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out; } @@ -649,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_cache; + ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -1095,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb) static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) - kmem_cache_free(skb_small_head_cache, head); + kmem_cache_free(net_hotdata.skb_small_head_cache, head); else kfree(head); } @@ -1162,7 +1158,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -1183,7 +1179,7 @@ static void kfree_skbmem(struct sk_buff *skb) if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: - kmem_cache_free(skbuff_fclone_cache, fclones); + kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) @@ -1280,7 +1276,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1305,7 +1301,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); + kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1467,9 +1463,9 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], - kmem_cache_size(skbuff_cache)); + kmem_cache_size(net_hotdata.skbuff_cache)); - kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -2066,7 +2062,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_cache, gfp_mask); + n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; @@ -5005,7 +5001,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", + net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| @@ -5013,7 +5009,7 @@ void __init skb_init(void) offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", + net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -5022,7 +5018,7 @@ void __init skb_init(void) * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ - skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, @@ -5895,7 +5891,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } diff --git a/net/core/xdp.c b/net/core/xdp.c index 0e3709a29175..41693154e426 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -16,6 +16,7 @@ #include #include +#include #include #include /* struct xdp_mem_allocator */ #include @@ -589,7 +590,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -658,7 +659,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; -- cgit v1.2.3 From 490a79faf95e705ba0ffd9ebf04a624b379e53c9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2024 16:00:30 +0000 Subject: net: introduce include/net/rps.h Move RPS related structures and helpers from include/linux/netdevice.h and include/net/sock.h to a new include file. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20240306160031.874438-18-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_arfs.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 1 + drivers/net/ethernet/sfc/rx_common.c | 1 + drivers/net/ethernet/sfc/siena/rx_common.c | 1 + drivers/net/tun.c | 1 + include/linux/netdevice.h | 82 -------------- include/net/rps.h | 127 ++++++++++++++++++++++ include/net/sock.h | 35 ------ net/core/dev.c | 1 + net/core/net-sysfs.c | 1 + net/core/sysctl_net_core.c | 1 + net/ipv4/af_inet.c | 1 + net/ipv4/tcp.c | 1 + net/ipv6/af_inet6.c | 1 + net/sctp/socket.c | 1 + 16 files changed, 140 insertions(+), 117 deletions(-) create mode 100644 include/net/rps.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index cca0e753f38f..7cee365cc7d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2018-2020, Intel Corporation. */ #include "ice.h" +#include /** * ice_is_arfs_active - helper to check is aRFS is active diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index d7da62cda821..5d3fde63b273 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index e66f486faafe..c7f542d0b8f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "en.h" #define ARFS_HASH_SHIFT BITS_PER_BYTE diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fac227d372db..dcd901eccfc8 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include #include +#include #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c index 4579f43484c3..219fb358a646 100644 --- a/drivers/net/ethernet/sfc/siena/rx_common.c +++ b/drivers/net/ethernet/sfc/siena/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include #include +#include #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8d258e263f54..0b3f21cba552 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -78,6 +78,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd641297e807..416a800d72ba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -225,12 +225,6 @@ struct net_device_core_stats { #include #include -#ifdef CONFIG_RPS -#include -extern struct static_key_false rps_needed; -extern struct static_key_false rfs_needed; -#endif - struct neighbour; struct neigh_parms; struct sk_buff; @@ -730,86 +724,10 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node #endif } -#ifdef CONFIG_RPS -/* - * This structure holds an RPS map which can be of variable length. The - * map is an array of CPUs. - */ -struct rps_map { - unsigned int len; - struct rcu_head rcu; - u16 cpus[]; -}; -#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) - -/* - * The rps_dev_flow structure contains the mapping of a flow to a CPU, the - * tail pointer for that CPU's input queue at the time of last enqueue, and - * a hardware filter index. - */ -struct rps_dev_flow { - u16 cpu; - u16 filter; - unsigned int last_qtail; -}; -#define RPS_NO_FILTER 0xffff - -/* - * The rps_dev_flow_table structure contains a table of flow mappings. - */ -struct rps_dev_flow_table { - unsigned int mask; - struct rcu_head rcu; - struct rps_dev_flow flows[]; -}; -#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ - ((_num) * sizeof(struct rps_dev_flow))) - -/* - * The rps_sock_flow_table contains mappings of flows to the last CPU - * on which they were processed by the application (set in recvmsg). - * Each entry is a 32bit value. Upper part is the high-order bits - * of flow hash, lower part is CPU number. - * rps_cpu_mask is used to partition the space, depending on number of - * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 - * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, - * meaning we use 32-6=26 bits for the hash. - */ -struct rps_sock_flow_table { - u32 mask; - - u32 ents[] ____cacheline_aligned_in_smp; -}; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) - -#define RPS_NO_CPU 0xffff - -extern u32 rps_cpu_mask; -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - -static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) { - unsigned int index = hash & table->mask; - u32 val = hash & ~rps_cpu_mask; - - /* We only give a hint, preemption can change CPU under us */ - val |= raw_smp_processor_id(); - - /* The following WRITE_ONCE() is paired with the READ_ONCE() - * here, and another one in get_rps_cpu(). - */ - if (READ_ONCE(table->ents[index]) != val) - WRITE_ONCE(table->ents[index], val); - } -} - #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif -#endif /* CONFIG_RPS */ /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { diff --git a/include/net/rps.h b/include/net/rps.h new file mode 100644 index 000000000000..6081d817d245 --- /dev/null +++ b/include/net/rps.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_RPS_H +#define _NET_RPS_H + +#include +#include +#include + +#ifdef CONFIG_RPS + +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; + +/* + * This structure holds an RPS map which can be of variable length. The + * map is an array of CPUs. + */ +struct rps_map { + unsigned int len; + struct rcu_head rcu; + u16 cpus[]; +}; +#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) + +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. + */ +struct rps_dev_flow { + u16 cpu; + u16 filter; + unsigned int last_qtail; +}; +#define RPS_NO_FILTER 0xffff + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct rps_dev_flow flows[]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + ((_num) * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high-order bits + * of flow hash, lower part is CPU number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. + */ +struct rps_sock_flow_table { + u32 mask; + + u32 ents[] ____cacheline_aligned_in_smp; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) + +#define RPS_NO_CPU 0xffff + +extern u32 rps_cpu_mask; +extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + unsigned int index = hash & table->mask; + u32 val = hash & ~rps_cpu_mask; + + /* We only give a hint, preemption can change CPU under us */ + val |= raw_smp_processor_id(); + + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); +} + +#endif /* CONFIG_RPS */ + +static inline void sock_rps_record_flow_hash(__u32 hash) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + if (!hash) + return; + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (sock_flow_table) + rps_record_sock_flow(sock_flow_table, hash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + if (static_branch_unlikely(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } + } +#endif +} + +#endif /* _NET_RPS_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 09a0cde8bf52..b5e00702acc1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1117,41 +1117,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } -static inline void sock_rps_record_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - -static inline void sock_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - if (static_branch_unlikely(&rfs_needed)) { - /* Reading sk->sk_rxhash might incur an expensive cache line - * miss. - * - * TCP_ESTABLISHED does cover almost all states where RFS - * might be useful, and is cheaper [1] than testing : - * IPv4: inet_sk(sk)->inet_daddr - * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) - * OR an additional socket flag - * [1] : sk_state and sk_prot are in the same cache line. - */ - if (sk->sk_state == TCP_ESTABLISHED) { - /* This READ_ONCE() is paired with the WRITE_ONCE() - * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). - */ - sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); - } - } -#endif -} static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) diff --git a/net/core/dev.c b/net/core/dev.c index 40ba02e04bcb..bcf49b0393d2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -155,6 +155,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index af238026ac3c..5560083774b1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8a4c698dad9c..4b93e27404e8 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "dev.h" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6f1cfd176e7b..55bd72997b31 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #endif #include #include +#include #include diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e1b848398d0..c5b83875411a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include #include #include +#include /* Track pending CMSGs. */ enum { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b90d46533cdc..8041dc181bd4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b9fcdb0952a..c67679a41044 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -67,6 +67,7 @@ #include #include #include +#include /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); -- cgit v1.2.3 From ab63a2387cb906d43b72a8effb611bbaecb2d0cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Mar 2024 11:55:07 -0800 Subject: netdev: add per-queue statistics The ethtool-nl family does a good job exposing various protocol related and IEEE/IETF statistics which used to get dumped under ethtool -S, with creative names. Queue stats don't have a netlink API, yet, and remain a lion's share of ethtool -S output for new drivers. Not only is that bad because the names differ driver to driver but it's also bug-prone. Intuitively drivers try to report only the stats for active queues, but querying ethtool stats involves multiple system calls, and the number of stats is read separately from the stats themselves. Worse still when user space asks for values of the stats, it doesn't inform the kernel how big the buffer is. If number of stats increases in the meantime kernel will overflow user buffer. Add a netlink API for dumping queue stats. Queue information is exposed via the netdev-genl family, so add the stats there. Support per-queue and sum-for-device dumps. Latter will be useful when subsequent patches add more interesting common stats than just bytes and packets. The API does not currently distinguish between HW and SW stats. The expectation is that the source of the stats will either not matter much (good packets) or be obvious (skb alloc errors). Acked-by: Stanislav Fomichev Reviewed-by: Amritha Nambiar Reviewed-by: Xuan Zhuo Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 84 +++++++++++++ Documentation/networking/statistics.rst | 15 +++ include/linux/netdevice.h | 3 + include/net/netdev_queues.h | 54 ++++++++ include/uapi/linux/netdev.h | 19 +++ net/core/netdev-genl-gen.c | 12 ++ net/core/netdev-genl-gen.h | 2 + net/core/netdev-genl.c | 213 ++++++++++++++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 19 +++ 9 files changed, 421 insertions(+) (limited to 'include/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 3addac970680..a1e48c3c84c9 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -74,6 +74,10 @@ definitions: name: queue-type type: enum entries: [ rx, tx ] + - + name: qstats-scope + type: flags + entries: [ queue ] attribute-sets: - @@ -265,6 +269,66 @@ attribute-sets: doc: ID of the NAPI instance which services this queue. type: u32 + - + name: qstats + doc: | + Get device statistics, scoped to a device or a queue. + These statistics extend (and partially duplicate) statistics available + in struct rtnl_link_stats64. + Value of the `scope` attribute determines how statistics are + aggregated. When aggregated for the entire device the statistics + represent the total number of events since last explicit reset of + the device (i.e. not a reconfiguration like changing queue count). + When reported per-queue, however, the statistics may not add + up to the total number of events, will only be reported for currently + active objects, and will likely report the number of events since last + reconfiguration. + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which stats belong. + type: u32 + checks: + min: 1 + - + name: queue-type + doc: Queue type as rx, tx, for queue-id. + type: u32 + enum: queue-type + - + name: queue-id + doc: Queue ID, if stats are scoped to a single queue instance. + type: u32 + - + name: scope + doc: | + What object type should be used to iterate over the stats. + type: uint + enum: qstats-scope + - + name: rx-packets + doc: | + Number of wire packets successfully received and passed to the stack. + For drivers supporting XDP, XDP is considered the first layer + of the stack, so packets consumed by XDP are still counted here. + type: uint + value: 8 # reserve some attr ids in case we need more metadata later + - + name: rx-bytes + doc: Successfully received bytes, see `rx-packets`. + type: uint + - + name: tx-packets + doc: | + Number of wire packets successfully sent. Packet is considered to be + successfully sent once it is in device memory (usually this means + the device has issued a DMA completion for the packet). + type: uint + - + name: tx-bytes + doc: Successfully sent bytes, see `tx-packets`. + type: uint + operations: list: - @@ -405,6 +469,26 @@ operations: attributes: - ifindex reply: *napi-get-op + - + name: qstats-get + doc: | + Get / dump fine grained statistics. Which statistics are reported + depends on the device and the driver, and whether the driver stores + software counters per-queue. + attribute-set: qstats + dump: + request: + attributes: + - scope + reply: + attributes: + - ifindex + - queue-type + - queue-id + - rx-packets + - rx-bytes + - tx-packets + - tx-bytes mcast-groups: list: diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 551b3cc29a41..75e017dfa825 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -41,6 +41,15 @@ If `-s` is specified once the detailed errors won't be shown. `ip` supports JSON formatting via the `-j` option. +Queue statistics +~~~~~~~~~~~~~~~~ + +Queue statistics are accessible via the netdev netlink family. + +Currently no widely distributed CLI exists to access those statistics. +Kernel development tools (ynl) can be used to experiment with them, +see `Documentation/userspace-api/netlink/intro-specs.rst`. + Protocol-specific statistics ---------------------------- @@ -147,6 +156,12 @@ Statistics are reported both in the responses to link information requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`, when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request). +netdev (netlink) +~~~~~~~~~~~~~~~~ + +`netdev` generic netlink family allows accessing page pool and per queue +statistics. + ethtool ------- diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 416a800d72ba..4230c7f3b959 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1955,6 +1955,7 @@ enum netdev_reg_state { * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops + * @stat_ops: Optional ops for queue-aware statistics * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2335,6 +2336,8 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; + const struct netdev_stat_ops *stat_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 8b8ed4e13d74..d633347eeda5 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,60 @@ #include +struct netdev_queue_stats_rx { + u64 bytes; + u64 packets; +}; + +struct netdev_queue_stats_tx { + u64 bytes; + u64 packets; +}; + +/** + * struct netdev_stat_ops - netdev ops for fine grained stats + * @get_queue_stats_rx: get stats for a given Rx queue + * @get_queue_stats_tx: get stats for a given Tx queue + * @get_base_stats: get base stats (not belonging to any live instance) + * + * Query stats for a given object. The values of the statistics are undefined + * on entry (specifically they are *not* zero-initialized). Drivers should + * assign values only to the statistics they collect. Statistics which are not + * collected must be left undefined. + * + * Queue objects are not necessarily persistent, and only currently active + * queues are queried by the per-queue callbacks. This means that per-queue + * statistics will not generally add up to the total number of events for + * the device. The @get_base_stats callback allows filling in the delta + * between events for currently live queues and overall device history. + * When the statistics for the entire device are queried, first @get_base_stats + * is issued to collect the delta, and then a series of per-queue callbacks. + * Only statistics which are set in @get_base_stats will be reported + * at the device level, meaning that unlike in queue callbacks, setting + * a statistic to zero in @get_base_stats is a legitimate thing to do. + * This is because @get_base_stats has a second function of designating which + * statistics are in fact correct for the entire device (e.g. when history + * for some of the events is not maintained, and reliable "total" cannot + * be provided). + * + * Device drivers can assume that when collecting total device stats, + * the @get_base_stats and subsequent per-queue calls are performed + * "atomically" (without releasing the rtnl_lock). + * + * Device drivers are encouraged to reset the per-queue statistics when + * number of queues change. This is because the primary use case for + * per-queue statistics is currently to detect traffic imbalance. + */ +struct netdev_stat_ops { + void (*get_queue_stats_rx)(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *stats); + void (*get_queue_stats_tx)(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *stats); + void (*get_base_stats)(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 93cb411adf72..639ffa04c172 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -132,6 +136,20 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) }; +enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -144,6 +162,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..8d8ace9ef87f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_QSTATS_GET - dump */ +static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_QSTATS_GET, + .dumpit = netdev_nl_qstats_get_dumpit, + .policy = netdev_qstats_get_nl_policy, + .maxattr = NETDEV_A_QSTATS_SCOPE, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..4db40fd5b4a9 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 918b109e0cf4..7fa75e13dc6d 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include "netdev-genl-gen.h" @@ -460,6 +461,218 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return err; } +#define NETDEV_STAT_NOT_SET (~0ULL) + +static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) +{ + const u64 *add = _add; + u64 *sum = _sum; + + while (size) { + if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) + *sum += *add; + sum++; + add++; + size -= 8; + } +} + +static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) +{ + if (value == NETDEV_STAT_NOT_SET) + return 0; + return nla_put_uint(rsp, attr_id, value); +} + +static int +netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, + u32 q_type, int i, const struct genl_info *info) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + memset(&rx, 0xff, sizeof(rx)); + ops->get_queue_stats_rx(netdev, i, &rx); + if (!memchr_inv(&rx, 0xff, sizeof(rx))) + goto nla_cancel; + if (netdev_nl_stats_write_rx(rsp, &rx)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + memset(&tx, 0xff, sizeof(tx)); + ops->get_queue_stats_tx(netdev, i, &tx); + if (!memchr_inv(&tx, 0xff, sizeof(tx))) + goto nla_cancel; + if (netdev_nl_stats_write_tx(rsp, &tx)) + goto nla_put_failure; + break; + } + + genlmsg_end(rsp, hdr); + return 0; + +nla_cancel: + genlmsg_cancel(rsp, hdr); + return 0; +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int +netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + int i, err; + + if (!(netdev->flags & IFF_UP)) + return 0; + + i = ctx->rxq_idx; + while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, + i, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + i = ctx->txq_idx; + while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, + i, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + return 0; +} + +static int +netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info) +{ + struct netdev_queue_stats_rx rx_sum, rx; + struct netdev_queue_stats_tx tx_sum, tx; + const struct netdev_stat_ops *ops; + void *hdr; + int i; + + ops = netdev->stat_ops; + /* Netdev can't guarantee any complete counters */ + if (!ops->get_base_stats) + return 0; + + memset(&rx_sum, 0xff, sizeof(rx_sum)); + memset(&tx_sum, 0xff, sizeof(tx_sum)); + + ops->get_base_stats(netdev, &rx_sum, &tx_sum); + + /* The op was there, but nothing reported, don't bother */ + if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && + !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + for (i = 0; i < netdev->real_num_rx_queues; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); + } + for (i = 0; i < netdev->real_num_tx_queues; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); + } + + if (netdev_nl_stats_write_rx(rsp, &rx_sum) || + netdev_nl_stats_write_tx(rsp, &tx_sum)) + goto nla_put_failure; + + genlmsg_end(rsp, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + unsigned int scope; + int err = 0; + + scope = 0; + if (info->attrs[NETDEV_A_QSTATS_SCOPE]) + scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); + + rtnl_lock(); + for_each_netdev_dump(net, netdev, ctx->ifindex) { + if (!netdev->stat_ops) + continue; + + switch (scope) { + case 0: + err = netdev_nl_stats_by_netdev(netdev, skb, info); + break; + case NETDEV_QSTATS_SCOPE_QUEUE: + err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); + break; + } + if (err < 0) + break; + } + rtnl_unlock(); + + return err; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 93cb411adf72..639ffa04c172 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -132,6 +136,20 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) }; +enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -144,6 +162,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From 6025b9135f7a8b46826a5fcf947259da43bac281 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Mar 2024 06:08:47 -0800 Subject: net: dqs: add NIC stall detector based on BQL softnet_data->time_squeeze is sometimes used as a proxy for host overload or indication of scheduling problems. In practice this statistic is very noisy and has hard to grasp units - e.g. is 10 squeezes a second to be expected, or high? Delaying network (NAPI) processing leads to drops on NIC queues but also RTT bloat, impacting pacing and CA decisions. Stalls are a little hard to detect on the Rx side, because there may simply have not been any packets received in given period of time. Packet timestamps help a little bit, but again we don't know if packets are stale because we're not keeping up or because someone (*cough* cgroups) disabled IRQs for a long time. We can, however, use Tx as a proxy for Rx stalls. Most drivers use combined Rx+Tx NAPIs so if Tx gets starved so will Rx. On the Tx side we know exactly when packets get queued, and completed, so there is no uncertainty. This patch adds stall checks to BQL. Why BQL? Because it's a convenient place to add such checks, already called by most drivers, and it has copious free space in its structures (this patch adds no extra cache references or dirtying to the fast path). The algorithm takes one parameter - max delay AKA stall threshold and increments a counter whenever NAPI got delayed for at least that amount of time. It also records the length of the longest stall. To be precise every time NAPI has not polled for at least stall thrs we check if there were any Tx packets queued between last NAPI run and now - stall_thrs/2. Unlike the classic Tx watchdog this mechanism does not ignore stalls caused by Tx being disabled, or loss of link. I don't think the check is worth the complexity, and stall is a stall, whether due to host overload, flow control, link down... doesn't matter much to the application. We have been running this detector in production at Meta for 2 years, with the threshold of 8ms. It's the lowest value where false positives become rare. There's still a constant stream of reported stalls (especially without the ksoftirqd deferral patches reverted), those who like their stall metrics to be 0 may prefer higher value. Signed-off-by: Jakub Kicinski Signed-off-by: Breno Leitao Signed-off-by: David S. Miller --- Documentation/ABI/testing/sysfs-class-net-queues | 23 ++++++++ include/linux/dynamic_queue_limits.h | 45 ++++++++++++++ include/trace/events/napi.h | 33 +++++++++++ lib/dynamic_queue_limits.c | 74 ++++++++++++++++++++++++ net/core/net-sysfs.c | 62 ++++++++++++++++++++ 5 files changed, 237 insertions(+) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 5bff64d256c2..84aa25e0d14d 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -96,3 +96,26 @@ Description: Indicates the absolute minimum limit of bytes allowed to be queued on this network device transmit queue. Default value is 0. + +What: /sys/class/net//queues/tx-/byte_queue_limits/stall_thrs +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Tx completion stall detection threshold in ms. Kernel will + guarantee to detect all stalls longer than this threshold but + may also detect stalls longer than half of the threshold. + +What: /sys/class/net//queues/tx-/byte_queue_limits/stall_cnt +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Number of detected Tx completion stalls. + +What: /sys/class/net//queues/tx-/byte_queue_limits/stall_max +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Longest detected Tx completion stall. Write 0 to clear. diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 407c2f281b64..5693a4be0d9a 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -38,14 +38,22 @@ #ifdef __KERNEL__ +#include #include +#define DQL_HIST_LEN 4 +#define DQL_HIST_ENT(dql, idx) ((dql)->history[(idx) % DQL_HIST_LEN]) + struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + unsigned long history_head; /* top 58 bits of jiffies */ + /* stall entries, a bit per entry */ + unsigned long history[DQL_HIST_LEN]; + /* Fields accessed only by completion path (dql_completed) */ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */ @@ -62,6 +70,13 @@ struct dql { unsigned int max_limit; /* Max limit */ unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ + + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + /* Longest stall detected, reported to user */ + unsigned short stall_max; + unsigned long last_reap; /* Last reap (in jiffies) */ + unsigned long stall_cnt; /* Number of stalls */ }; /* Set some static maximums */ @@ -74,6 +89,8 @@ struct dql { */ static inline void dql_queued(struct dql *dql, unsigned int count) { + unsigned long map, now, now_hi, i; + BUG_ON(count > DQL_MAX_OBJECT); dql->last_obj_cnt = count; @@ -86,6 +103,34 @@ static inline void dql_queued(struct dql *dql, unsigned int count) barrier(); dql->num_queued += count; + + now = jiffies; + now_hi = now / BITS_PER_LONG; + + /* The following code set a bit in the ring buffer, where each + * bit trackes time the packet was queued. The dql->history buffer + * tracks DQL_HIST_LEN * BITS_PER_LONG time (jiffies) slot + */ + if (unlikely(now_hi != dql->history_head)) { + /* About to reuse slots, clear them */ + for (i = 0; i < DQL_HIST_LEN; i++) { + /* Multiplication masks high bits */ + if (now_hi * BITS_PER_LONG == + (dql->history_head + i) * BITS_PER_LONG) + break; + DQL_HIST_ENT(dql, dql->history_head + i + 1) = 0; + } + /* pairs with smp_rmb() in dql_check_stall() */ + smp_wmb(); + WRITE_ONCE(dql->history_head, now_hi); + } + + /* __set_bit() does not guarantee WRITE_ONCE() semantics */ + map = DQL_HIST_ENT(dql, now_hi); + + /* Populate the history with an entry (bit) per queued */ + if (!(map & BIT_MASK(now))) + WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } /* Returns how many objects can be queued, < 0 indicates over limit. */ diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 6678cf8b235b..dc03cf8e0369 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -36,6 +36,39 @@ TRACE_EVENT(napi_poll, __entry->work, __entry->budget) ); +TRACE_EVENT(dql_stall_detected, + + TP_PROTO(unsigned short thrs, unsigned int len, + unsigned long last_reap, unsigned long hist_head, + unsigned long now, unsigned long *hist), + + TP_ARGS(thrs, len, last_reap, hist_head, now, hist), + + TP_STRUCT__entry( + __field( unsigned short, thrs) + __field( unsigned int, len) + __field( unsigned long, last_reap) + __field( unsigned long, hist_head) + __field( unsigned long, now) + __array( unsigned long, hist, 4) + ), + + TP_fast_assign( + __entry->thrs = thrs; + __entry->len = len; + __entry->last_reap = last_reap; + __entry->hist_head = hist_head * BITS_PER_LONG; + __entry->now = now; + memcpy(__entry->hist, hist, sizeof(entry->hist)); + ), + + TP_printk("thrs %u len %u last_reap %lu hist_head %lu now %lu hist %016lx %016lx %016lx %016lx", + __entry->thrs, __entry->len, + __entry->last_reap, __entry->hist_head, __entry->now, + __entry->hist[0], __entry->hist[1], + __entry->hist[2], __entry->hist[3]) +); + #undef NO_DEV #endif /* _TRACE_NAPI_H */ diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index fde0aa244148..a1389db1c30a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -10,10 +10,77 @@ #include #include #include +#include #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) +static void dql_check_stall(struct dql *dql) +{ + unsigned short stall_thrs; + unsigned long now; + + stall_thrs = READ_ONCE(dql->stall_thrs); + if (!stall_thrs) + return; + + now = jiffies; + /* Check for a potential stall */ + if (time_after_eq(now, dql->last_reap + stall_thrs)) { + unsigned long hist_head, t, start, end; + + /* We are trying to detect a period of at least @stall_thrs + * jiffies without any Tx completions, but during first half + * of which some Tx was posted. + */ +dqs_again: + hist_head = READ_ONCE(dql->history_head); + /* pairs with smp_wmb() in dql_queued() */ + smp_rmb(); + + /* Get the previous entry in the ring buffer, which is the + * oldest sample. + */ + start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; + + /* Advance start to continue from the last reap time */ + if (time_before(start, dql->last_reap + 1)) + start = dql->last_reap + 1; + + /* Newest sample we should have already seen a completion for */ + end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); + + /* Shrink the search space to [start, (now - start_thrs/2)] if + * `end` is beyond the stall zone + */ + if (time_before(now, end + stall_thrs / 2)) + end = now - stall_thrs / 2; + + /* Search for the queued time in [t, end] */ + for (t = start; time_before_eq(t, end); t++) + if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), + dql->history)) + break; + + /* Variable t contains the time of the queue */ + if (!time_before_eq(t, end)) + goto no_stall; + + /* The ring buffer was modified in the meantime, retry */ + if (hist_head != READ_ONCE(dql->history_head)) + goto dqs_again; + + dql->stall_cnt++; + dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); + + trace_dql_stall_detected(dql->stall_thrs, now - t, + dql->last_reap, dql->history_head, + now, dql->history); + } +no_stall: + dql->last_reap = now; +} + /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { @@ -110,6 +177,8 @@ void dql_completed(struct dql *dql, unsigned int count) dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; + + dql_check_stall(dql); } EXPORT_SYMBOL(dql_completed); @@ -125,6 +194,10 @@ void dql_reset(struct dql *dql) dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; + + dql->last_reap = jiffies; + dql->history_head = jiffies / BITS_PER_LONG; + memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); @@ -133,6 +206,7 @@ void dql_init(struct dql *dql, unsigned int hold_time) dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; + dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5560083774b1..e3d7a8cfa20b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1415,6 +1415,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); +static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); +} + +static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + value = msecs_to_jiffies(value); + if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) + return -ERANGE; + + if (!dql->stall_thrs && value) + dql->last_reap = jiffies; + /* Force last_reap to be live */ + smp_wmb(); + dql->stall_thrs = value; + + return len; +} + +static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = + __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); + +static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) +{ + return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); +} + +static ssize_t bql_set_stall_max(struct netdev_queue *queue, + const char *buf, size_t len) +{ + WRITE_ONCE(queue->dql.stall_max, 0); + return len; +} + +static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = + __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); + +static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%lu\n", dql->stall_cnt); +} + +static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = + __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); + static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { @@ -1453,6 +1512,9 @@ static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, + &bql_stall_thrs_attribute.attr, + &bql_stall_cnt_attribute.attr, + &bql_stall_max_attribute.attr, NULL }; -- cgit v1.2.3 From 1cface552a5b5f6e53a855de1a503ff958e2e253 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Mar 2024 12:34:46 +0000 Subject: net: add skb_data_unref() helper Similar to skb_unref(), add skb_data_unref() to save an expensive atomic operation (and cache line dirtying) when last reference on shinfo->dataref is released. I saw this opportunity on hosts with RAW sockets accidentally bound to UDP protocol, forcing an skb_clone() on all received packets. These RAW sockets had their receive queue full, so all clone packets were immediately dropped. When UDP recvmsg() consumes later the original skb, skb_release_data() is hitting atomic_sub_return() quite badly, because skb->clone has been set permanently. Note that this patch helps TCP TX performance, because TCP stack also use (fast) clones. This means that at least one of the two packets (the main skb or its clone) will no longer have to perform this atomic operation in skb_release_data(). Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20240307123446.2302230-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 18 ++++++++++++++++++ net/core/skbuff.c | 4 +--- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d0508f90bed5..3023bc2be6a1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1237,6 +1237,24 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } +static inline bool skb_data_unref(const struct sk_buff *skb, + struct skb_shared_info *shinfo) +{ + int bias; + + if (!skb->cloned) + return true; + + bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; + + if (atomic_read(&shinfo->dataref) == bias) + smp_rmb(); + else if (atomic_sub_return(bias, &shinfo->dataref)) + return false; + + return true; +} + void __fix_address kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 766219011aea..b99127712e67 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1115,9 +1115,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason, struct skb_shared_info *shinfo = skb_shinfo(skb); int i; - if (skb->cloned && - atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, - &shinfo->dataref)) + if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { -- cgit v1.2.3 From de5f84338970815b9fdd3497a975fb572d11e0b5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 7 Mar 2024 12:39:06 +0100 Subject: lib/bitmap: Introduce bitmap_scatter() and bitmap_gather() helpers These helpers scatters or gathers a bitmap with the help of the mask position bits parameter. bitmap_scatter() does the following: src: 0000000001011010 |||||| +------+||||| | +----+|||| | |+----+||| | || +-+|| | || | || mask: ...v..vv...v..vv ...0..11...0..10 dst: 0000001100000010 and bitmap_gather() performs this one: mask: ...v..vv...v..vv src: 0000001100000010 ^ ^^ ^ 0 | || | 10 | || > 010 | |+--> 1010 | +--> 11010 +----> 011010 dst: 0000000000011010 bitmap_gather() can the seen as the reverse bitmap_scatter() operation. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/lkml/20230926052007.3917389-3-andriy.shevchenko@linux.intel.com/ Co-developed-by: Herve Codina Signed-off-by: Herve Codina Acked-by: Yury Norov Signed-off-by: David S. Miller --- include/linux/bitmap.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/test_bitmap.c | 42 ++++++++++++++++++++ 2 files changed, 143 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5814e9ee40ba..00b8c6d4355c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -63,6 +63,8 @@ struct device; * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) + * bitmap_scatter(dst, src, mask, nbits) *dst = map(dense, sparse)(src) + * bitmap_gather(dst, src, mask, nbits) *dst = map(sparse, dense)(src) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap @@ -499,6 +501,105 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } +/** + * bitmap_scatter - Scatter a bitmap according to the given mask + * @dst: scattered bitmap + * @src: gathered bitmap + * @mask: mask representing bits to assign to in the scattered bitmap + * @nbits: number of bits in each of these bitmaps + * + * Scatters bitmap with sequential bits according to the given @mask. + * + * Example: + * If @src bitmap = 0x005a, with @mask = 0x1313, @dst will be 0x0302. + * + * Or in binary form + * @src @mask @dst + * 0000000001011010 0001001100010011 0000001100000010 + * + * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12) + * + * A more 'visual' description of the operation: + * src: 0000000001011010 + * |||||| + * +------+||||| + * | +----+|||| + * | |+----+||| + * | || +-+|| + * | || | || + * mask: ...v..vv...v..vv + * ...0..11...0..10 + * dst: 0000001100000010 + * + * A relationship exists between bitmap_scatter() and bitmap_gather(). + * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. + * See bitmap_scatter() for details related to this relationship. + */ +static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int n = 0; + unsigned int bit; + + bitmap_zero(dst, nbits); + + for_each_set_bit(bit, mask, nbits) + __assign_bit(bit, dst, test_bit(n++, src)); +} + +/** + * bitmap_gather - Gather a bitmap according to given mask + * @dst: gathered bitmap + * @src: scattered bitmap + * @mask: mask representing bits to extract from in the scattered bitmap + * @nbits: number of bits in each of these bitmaps + * + * Gathers bitmap with sparse bits according to the given @mask. + * + * Example: + * If @src bitmap = 0x0302, with @mask = 0x1313, @dst will be 0x001a. + * + * Or in binary form + * @src @mask @dst + * 0000001100000010 0001001100010011 0000000000011010 + * + * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5) + * + * A more 'visual' description of the operation: + * mask: ...v..vv...v..vv + * src: 0000001100000010 + * ^ ^^ ^ 0 + * | || | 10 + * | || > 010 + * | |+--> 1010 + * | +--> 11010 + * +----> 011010 + * dst: 0000000000011010 + * + * A relationship exists between bitmap_gather() and bitmap_scatter(). See + * bitmap_scatter() for the bitmap scatter detailed operations. + * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n). + * The operation bitmap_gather(result, scattered, mask, n) leads to a result + * equal or equivalent to src. + * + * The result can be 'equivalent' because bitmap_scatter() and bitmap_gather() + * are not bijective. + * The result and src values are equivalent in that sense that a call to + * bitmap_scatter(res, src, mask, n) and a call to + * bitmap_scatter(res, result, mask, n) will lead to the same res value. + */ +static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int n = 0; + unsigned int bit; + + bitmap_zero(dst, nbits); + + for_each_set_bit(bit, mask, nbits) + __assign_bit(n++, dst, test_bit(bit, src)); +} + static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 65f22c2578b0..6b2b33579f56 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -380,6 +380,47 @@ static void __init test_replace(void) expect_eq_bitmap(bmap, exp3_1_0, nbits); } +static const unsigned long sg_mask[] __initconst = { + BITMAP_FROM_U64(0x000000000000035aULL), +}; + +static const unsigned long sg_src[] __initconst = { + BITMAP_FROM_U64(0x0000000000000667ULL), +}; + +static const unsigned long sg_gather_exp[] __initconst = { + BITMAP_FROM_U64(0x0000000000000029ULL), +}; + +static const unsigned long sg_scatter_exp[] __initconst = { + BITMAP_FROM_U64(0x000000000000021aULL), +}; + +static void __init test_bitmap_sg(void) +{ + unsigned int nbits = 64; + DECLARE_BITMAP(bmap_gather, 100); + DECLARE_BITMAP(bmap_scatter, 100); + DECLARE_BITMAP(bmap_tmp, 100); + DECLARE_BITMAP(bmap_res, 100); + + /* Simple gather call */ + bitmap_zero(bmap_gather, 100); + bitmap_gather(bmap_gather, sg_src, sg_mask, nbits); + expect_eq_bitmap(sg_gather_exp, bmap_gather, nbits); + + /* Simple scatter call */ + bitmap_zero(bmap_scatter, 100); + bitmap_scatter(bmap_scatter, sg_src, sg_mask, nbits); + expect_eq_bitmap(sg_scatter_exp, bmap_scatter, nbits); + + /* Scatter/gather relationship */ + bitmap_zero(bmap_tmp, 100); + bitmap_gather(bmap_tmp, bmap_scatter, sg_mask, nbits); + bitmap_scatter(bmap_res, bmap_tmp, sg_mask, nbits); + expect_eq_bitmap(bmap_scatter, bmap_res, nbits); +} + #define PARSE_TIME 0x1 #define NO_LEN 0x2 @@ -1252,6 +1293,7 @@ static void __init selftest(void) test_copy(); test_bitmap_region(); test_replace(); + test_bitmap_sg(); test_bitmap_arr32(); test_bitmap_arr64(); test_bitmap_parse(); -- cgit v1.2.3 From d7bca9199a27b8690ae1c71dc11f825154af7234 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 8 Mar 2024 09:12:54 -0800 Subject: mm: Introduce vmap_page_range() to map pages in PCI address space ioremap_page_range() should be used for ranges within vmalloc range only. The vmalloc ranges are allocated by get_vm_area(). PCI has "resource" allocator that manages PCI_IOBASE, IO_SPACE_LIMIT address range, hence introduce vmap_page_range() to be used exclusively to map pages in PCI address space. Fixes: 3e49a866c9dc ("mm: Enforce VM_IOREMAP flag and range in ioremap_page_range.") Reported-by: Miguel Ojeda Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Reviewed-by: Christoph Hellwig Tested-by: Miguel Ojeda Link: https://lore.kernel.org/bpf/CANiq72ka4rir+RTN2FQoT=Vvprp_Ao-CvoYEkSNqtSY+RZj+AA@mail.gmail.com --- arch/arm/mm/ioremap.c | 8 ++++---- arch/loongarch/kernel/setup.c | 2 +- arch/mips/loongson64/init.c | 2 +- arch/powerpc/kernel/isa-bridge.c | 4 ++-- drivers/pci/pci.c | 4 ++-- include/linux/io.h | 7 +++++++ mm/vmalloc.c | 23 +++++++++++++++-------- 7 files changed, 32 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 2129070065c3..794cfea9f9d4 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -110,8 +110,8 @@ void __init add_static_vm_early(struct static_vm *svm) int ioremap_page(unsigned long virt, unsigned long phys, const struct mem_type *mtype) { - return ioremap_page_range(virt, virt + PAGE_SIZE, phys, - __pgprot(mtype->prot_pte)); + return vmap_page_range(virt, virt + PAGE_SIZE, phys, + __pgprot(mtype->prot_pte)); } EXPORT_SYMBOL(ioremap_page); @@ -466,8 +466,8 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) if (res->end > IO_SPACE_LIMIT) return -EINVAL; - return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr, - __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte)); + return vmap_page_range(vaddr, vaddr + resource_size(res), phys_addr, + __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte)); } EXPORT_SYMBOL(pci_remap_iospace); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 634ef17fd38b..fd915ad69c09 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -490,7 +490,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, } vaddr = (unsigned long)(PCI_IOBASE + range->io_start); - ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); + vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); return 0; } diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 553142c1f14f..a35dd7311795 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -180,7 +180,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, resource_size_ vaddr = PCI_IOBASE + range->io_start; - ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); + vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); return 0; } diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 48e0eaf1ad61..5c064485197a 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -46,8 +46,8 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size) WARN_ON_ONCE(size & ~PAGE_MASK); if (slab_is_available()) { - if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa, - pgprot_noncached(PAGE_KERNEL))) + if (vmap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa, + pgprot_noncached(PAGE_KERNEL))) vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size); } else { early_ioremap_range(ISA_IO_BASE, pa, size, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c3585229c12a..ccee56615f78 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4353,8 +4353,8 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) if (res->end > IO_SPACE_LIMIT) return -EINVAL; - return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr, - pgprot_device(PAGE_KERNEL)); + return vmap_page_range(vaddr, vaddr + resource_size(res), phys_addr, + pgprot_device(PAGE_KERNEL)); #else /* * This architecture does not have memory mapped I/O space, diff --git a/include/linux/io.h b/include/linux/io.h index 7304f2a69960..235ba7d80a8f 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -23,12 +23,19 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot); +int vmap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot); #else static inline int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { return 0; } +static inline int vmap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) +{ + return 0; +} #endif /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e5b8c70950bc..1e36322d83d8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -304,11 +304,24 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end, return err; } +int vmap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) +{ + int err; + + err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), + ioremap_max_page_shift); + flush_cache_vmap(addr, end); + if (!err) + err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, + ioremap_max_page_shift); + return err; +} + int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { struct vm_struct *area; - int err; area = find_vm_area((void *)addr); if (!area || !(area->flags & VM_IOREMAP)) { @@ -322,13 +335,7 @@ int ioremap_page_range(unsigned long addr, unsigned long end, (long)area->addr + get_vm_area_size(area)); return -ERANGE; } - err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), - ioremap_max_page_shift); - flush_cache_vmap(addr, end); - if (!err) - err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, - ioremap_max_page_shift); - return err; + return vmap_page_range(addr, end, phys_addr, prot); } static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, -- cgit v1.2.3 From e5b7aefe38f7f6258935d8a10c36552dd957048a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Mar 2024 10:22:30 +0000 Subject: net: gro: move two declarations to include/net/gro.h Move gro_find_receive_by_type() and gro_find_complete_by_type() to include/net/gro.h where they belong. Also use _NET_GRO_H instead of _NET_IPV6_GRO_H to protect include/net/gro.h from multiple inclusions. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240308102230.296224-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 -- include/net/gro.h | 9 ++++++--- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4230c7f3b959..c6f6ac779b34 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3901,8 +3901,6 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); -struct packet_offload *gro_find_receive_by_type(__be16 type); -struct packet_offload *gro_find_complete_by_type(__be16 type); static inline void napi_free_frags(struct napi_struct *napi) { diff --git a/include/net/gro.h b/include/net/gro.h index d6fc8fbd3730..50f1e403dbbb 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_IPV6_GRO_H -#define _NET_IPV6_GRO_H +#ifndef _NET_GRO_H +#define _NET_GRO_H #include #include @@ -494,4 +494,7 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * #endif } -#endif /* _NET_IPV6_GRO_H */ +struct packet_offload *gro_find_receive_by_type(__be16 type); +struct packet_offload *gro_find_complete_by_type(__be16 type); + +#endif /* _NET_GRO_H */ -- cgit v1.2.3 From 317460317a02a1af512697e6e964298dedd8a163 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:07:59 -0800 Subject: bpf: Introduce bpf_arena. Introduce bpf_arena, which is a sparse shared memory region between the bpf program and user space. Use cases: 1. User space mmap-s bpf_arena and uses it as a traditional mmap-ed anonymous region, like memcached or any key/value storage. The bpf program implements an in-kernel accelerator. XDP prog can search for a key in bpf_arena and return a value without going to user space. 2. The bpf program builds arbitrary data structures in bpf_arena (hash tables, rb-trees, sparse arrays), while user space consumes it. 3. bpf_arena is a "heap" of memory from the bpf program's point of view. The user space may mmap it, but bpf program will not convert pointers to user base at run-time to improve bpf program speed. Initially, the kernel vm_area and user vma are not populated. User space can fault in pages within the range. While servicing a page fault, bpf_arena logic will insert a new page into the kernel and user vmas. The bpf program can allocate pages from that region via bpf_arena_alloc_pages(). This kernel function will insert pages into the kernel vm_area. The subsequent fault-in from user space will populate that page into the user vma. The BPF_F_SEGV_ON_FAULT flag at arena creation time can be used to prevent fault-in from user space. In such a case, if a page is not allocated by the bpf program and not present in the kernel vm_area, the user process will segfault. This is useful for use cases 2 and 3 above. bpf_arena_alloc_pages() is similar to user space mmap(). It allocates pages either at a specific address within the arena or allocates a range with the maple tree. bpf_arena_free_pages() is analogous to munmap(), which frees pages and removes the range from the kernel vm_area and from user process vmas. bpf_arena can be used as a bpf program "heap" of up to 4GB. The speed of bpf program is more important than ease of sharing with user space. This is use case 3. In such a case, the BPF_F_NO_USER_CONV flag is recommended. It will tell the verifier to treat the rX = bpf_arena_cast_user(rY) instruction as a 32-bit move wX = wY, which will improve bpf prog performance. Otherwise, bpf_arena_cast_user is translated by JIT to conditionally add the upper 32 bits of user vm_start (if the pointer is not NULL) to arena pointers before they are stored into memory. This way, user space sees them as valid 64-bit pointers. Diff https://github.com/llvm/llvm-project/pull/84410 enables LLVM BPF backend generate the bpf_addr_space_cast() instruction to cast pointers between address_space(1) which is reserved for bpf_arena pointers and default address space zero. All arena pointers in a bpf program written in C language are tagged as __attribute__((address_space(1))). Hence, clang provides helpful diagnostics when pointers cross address space. Libbpf and the kernel support only address_space == 1. All other address space identifiers are reserved. rX = bpf_addr_space_cast(rY, /* dst_as */ 1, /* src_as */ 0) tells the verifier that rX->type = PTR_TO_ARENA. Any further operations on PTR_TO_ARENA register have to be in the 32-bit domain. The verifier will mark load/store through PTR_TO_ARENA with PROBE_MEM32. JIT will generate them as kern_vm_start + 32bit_addr memory accesses. The behavior is similar to copy_from_kernel_nofault() except that no address checks are necessary. The address is guaranteed to be in the 4GB range. If the page is not present, the destination register is zeroed on read, and the operation is ignored on write. rX = bpf_addr_space_cast(rY, 0, 1) tells the verifier that rX->type = unknown scalar. If arena->map_flags has BPF_F_NO_USER_CONV set, then the verifier converts such cast instructions to mov32. Otherwise, JIT will emit native code equivalent to: rX = (u32)rY; if (rY) rX |= clear_lo32_bits(arena->user_vm_start); /* replace hi32 bits in rX */ After such conversion, the pointer becomes a valid user pointer within bpf_arena range. The user process can access data structures created in bpf_arena without any additional computations. For example, a linked list built by a bpf program can be walked natively by user space. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Reviewed-by: Barret Rhoden Link: https://lore.kernel.org/bpf/20240308010812.89848-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 7 +- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 10 + kernel/bpf/Makefile | 3 + kernel/bpf/arena.c | 558 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 11 + kernel/bpf/syscall.c | 36 +++ kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 10 + 9 files changed, 635 insertions(+), 2 deletions(-) create mode 100644 kernel/bpf/arena.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 95e07673cdc1..ea6ab6e0eef9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; +struct bpf_arena; struct sock; struct seq_file; struct btf; @@ -528,8 +529,8 @@ void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); - - +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena); +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -2215,6 +2216,8 @@ int generic_map_delete_batch(struct bpf_map *map, struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG_KMEM void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 94baced5a1ad..9f2a6b83b49e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -132,6 +132,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_ARENA, arena_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 85ec7fc799d7..e30d943db8a4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1009,6 +1009,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, __MAX_BPF_MAP_TYPE }; @@ -1396,6 +1397,12 @@ enum { /* BPF token FD is passed in a corresponding command's token_fd field */ BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), }; /* Flags for BPF_PROG_QUERY. */ @@ -1467,6 +1474,9 @@ union bpf_attr { * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the * number of hash functions (if 0, the bloom filter will default * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. */ __u64 map_extra; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 4ce95acfcaa7..368c5d86b5b7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -15,6 +15,9 @@ obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o +ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy) +obj-$(CONFIG_BPF_SYSCALL) += arena.o +endif obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c new file mode 100644 index 000000000000..86571e760dd6 --- /dev/null +++ b/kernel/bpf/arena.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include +#include +#include + +/* + * bpf_arena is a sparsely populated shared memory region between bpf program and + * user space process. + * + * For example on x86-64 the values could be: + * user_vm_start 7f7d26200000 // picked by mmap() + * kern_vm_start ffffc90001e69000 // picked by get_vm_area() + * For user space all pointers within the arena are normal 8-byte addresses. + * In this example 7f7d26200000 is the address of the first page (pgoff=0). + * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr + * (u32)7f7d26200000 -> 26200000 + * hence + * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb + * kernel memory region. + * + * BPF JITs generate the following code to access arena: + * mov eax, eax // eax has lower 32-bit of user pointer + * mov word ptr [rax + r12 + off], bx + * where r12 == kern_vm_start and off is s16. + * Hence allocate 4Gb + GUARD_SZ/2 on each side. + * + * Initially kernel vm_area and user vma are not populated. + * User space can fault-in any address which will insert the page + * into kernel and user vma. + * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc + * which will insert it into kernel vm_area. + * The later fault-in from user space will populate that page into user vma. + */ + +/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ +#define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8) +#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ) + +struct bpf_arena { + struct bpf_map map; + u64 user_vm_start; + u64 user_vm_end; + struct vm_struct *kern_vm; + struct maple_tree mt; + struct list_head vma_list; + struct mutex lock; +}; + +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0; +} + +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return arena ? arena->user_vm_start : 0; +} + +static long arena_map_peek_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static long arena_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + +static long compute_pgoff(struct bpf_arena *arena, long uaddr) +{ + return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT; +} + +static struct bpf_map *arena_map_alloc(union bpf_attr *attr) +{ + struct vm_struct *kern_vm; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_arena *arena; + u64 vm_range; + int err = -ENOMEM; + + if (attr->key_size || attr->value_size || attr->max_entries == 0 || + /* BPF_F_MMAPABLE must be set */ + !(attr->map_flags & BPF_F_MMAPABLE) || + /* No unsupported flags present */ + (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV))) + return ERR_PTR(-EINVAL); + + if (attr->map_extra & ~PAGE_MASK) + /* If non-zero the map_extra is an expected user VMA start address */ + return ERR_PTR(-EINVAL); + + vm_range = (u64)attr->max_entries * PAGE_SIZE; + if (vm_range > (1ull << 32)) + return ERR_PTR(-E2BIG); + + if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) + /* user vma must not cross 32-bit boundary */ + return ERR_PTR(-ERANGE); + + kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP); + if (!kern_vm) + return ERR_PTR(-ENOMEM); + + arena = bpf_map_area_alloc(sizeof(*arena), numa_node); + if (!arena) + goto err; + + arena->kern_vm = kern_vm; + arena->user_vm_start = attr->map_extra; + if (arena->user_vm_start) + arena->user_vm_end = arena->user_vm_start + vm_range; + + INIT_LIST_HEAD(&arena->vma_list); + bpf_map_init_from_attr(&arena->map, attr); + mt_init_flags(&arena->mt, MT_FLAGS_ALLOC_RANGE); + mutex_init(&arena->lock); + + return &arena->map; +err: + free_vm_area(kern_vm); + return ERR_PTR(err); +} + +static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data) +{ + struct page *page; + pte_t pte; + + pte = ptep_get(ptep); + if (!pte_present(pte)) /* sanity check */ + return 0; + page = pte_page(pte); + /* + * We do not update pte here: + * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug + * 2. TLB flushing is batched or deferred. Even if we clear pte, + * the TLB entries can stick around and continue to permit access to + * the freed page. So it all relies on 1. + */ + __free_page(page); + return 0; +} + +static void arena_map_free(struct bpf_map *map) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + /* + * Check that user vma-s are not around when bpf map is freed. + * mmap() holds vm_file which holds bpf_map refcnt. + * munmap() must have happened on vma followed by arena_vm_close() + * which would clear arena->vma_list. + */ + if (WARN_ON_ONCE(!list_empty(&arena->vma_list))) + return; + + /* + * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area(). + * It unmaps everything from vmalloc area and clears pgtables. + * Call apply_to_existing_page_range() first to find populated ptes and + * free those pages. + */ + apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena), + KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL); + free_vm_area(arena->kern_vm); + mtree_destroy(&arena->mt); + bpf_map_area_free(arena); +} + +static void *arena_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static long arena_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + return 0; +} + +static u64 arena_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + +struct vma_list { + struct vm_area_struct *vma; + struct list_head head; +}; + +static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) +{ + struct vma_list *vml; + + vml = kmalloc(sizeof(*vml), GFP_KERNEL); + if (!vml) + return -ENOMEM; + vma->vm_private_data = vml; + vml->vma = vma; + list_add(&vml->head, &arena->vma_list); + return 0; +} + +static void arena_vm_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct vma_list *vml; + + guard(mutex)(&arena->lock); + vml = vma->vm_private_data; + list_del(&vml->head); + vma->vm_private_data = NULL; + kfree(vml); +} + +#define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */ + +static vm_fault_t arena_vm_fault(struct vm_fault *vmf) +{ + struct bpf_map *map = vmf->vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct page *page; + long kbase, kaddr; + int ret; + + kbase = bpf_arena_get_kern_vm_start(arena); + kaddr = kbase + (u32)(vmf->address & PAGE_MASK); + + guard(mutex)(&arena->lock); + page = vmalloc_to_page((void *)kaddr); + if (page) + /* already have a page vmap-ed */ + goto out; + + if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT) + /* User space requested to segfault when page is not allocated by bpf prog */ + return VM_FAULT_SIGSEGV; + + ret = mtree_insert(&arena->mt, vmf->pgoff, MT_ENTRY, GFP_KERNEL); + if (ret) + return VM_FAULT_SIGSEGV; + + /* Account into memcg of the process that created bpf_arena */ + ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + return VM_FAULT_SIGSEGV; + } + + ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + __free_page(page); + return VM_FAULT_SIGSEGV; + } +out: + page_ref_add(page, 1); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct arena_vm_ops = { + .close = arena_vm_close, + .fault = arena_vm_fault, +}; + +static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + long ret; + + if (pgoff) + return -EINVAL; + if (len > (1ull << 32)) + return -E2BIG; + + /* if user_vm_start was specified at arena creation time */ + if (arena->user_vm_start) { + if (len > arena->user_vm_end - arena->user_vm_start) + return -E2BIG; + if (len != arena->user_vm_end - arena->user_vm_start) + return -EINVAL; + if (addr != arena->user_vm_start) + return -EINVAL; + } + + ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags); + if (IS_ERR_VALUE(ret)) + return ret; + if ((ret >> 32) == ((ret + len - 1) >> 32)) + return ret; + if (WARN_ON_ONCE(arena->user_vm_start)) + /* checks at map creation time should prevent this */ + return -EFAULT; + return round_up(ret, 1ull << 32); +} + +static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + guard(mutex)(&arena->lock); + if (arena->user_vm_start && arena->user_vm_start != vma->vm_start) + /* + * If map_extra was not specified at arena creation time then + * 1st user process can do mmap(NULL, ...) to pick user_vm_start + * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..); + * or + * specify addr in map_extra and + * use the same addr later with mmap(addr, MAP_FIXED..); + */ + return -EBUSY; + + if (arena->user_vm_end && arena->user_vm_end != vma->vm_end) + /* all user processes must have the same size of mmap-ed region */ + return -EBUSY; + + /* Earlier checks should prevent this */ + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff)) + return -EFAULT; + + if (remember_vma(arena, vma)) + return -ENOMEM; + + arena->user_vm_start = vma->vm_start; + arena->user_vm_end = vma->vm_end; + /* + * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and + * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid + * potential change of user_vm_start. + */ + vm_flags_set(vma, VM_DONTEXPAND); + vma->vm_ops = &arena_vm_ops; + return 0; +} + +static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if ((u64)off > arena->user_vm_end - arena->user_vm_start) + return -ERANGE; + *imm = (unsigned long)arena->user_vm_start; + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena) +const struct bpf_map_ops arena_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = arena_map_alloc, + .map_free = arena_map_free, + .map_direct_value_addr = arena_map_direct_value_addr, + .map_mmap = arena_map_mmap, + .map_get_unmapped_area = arena_get_unmapped_area, + .map_get_next_key = arena_map_get_next_key, + .map_push_elem = arena_map_push_elem, + .map_peek_elem = arena_map_peek_elem, + .map_pop_elem = arena_map_pop_elem, + .map_lookup_elem = arena_map_lookup_elem, + .map_update_elem = arena_map_update_elem, + .map_delete_elem = arena_map_delete_elem, + .map_check_btf = arena_map_check_btf, + .map_mem_usage = arena_map_mem_usage, + .map_btf_id = &bpf_arena_map_btf_ids[0], +}; + +static u64 clear_lo32(u64 val) +{ + return val & ~(u64)~0U; +} + +/* + * Allocate pages and vmap them into kernel vmalloc area. + * Later the pages will be mmaped into user space vma. + */ +static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id) +{ + /* user_vm_end/start are fixed before bpf prog runs */ + long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; + u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena); + struct page **pages; + long pgoff = 0; + u32 uaddr32; + int ret, i; + + if (page_cnt > page_cnt_max) + return 0; + + if (uaddr) { + if (uaddr & ~PAGE_MASK) + return 0; + pgoff = compute_pgoff(arena, uaddr); + if (pgoff + page_cnt > page_cnt_max) + /* requested address will be outside of user VMA */ + return 0; + } + + /* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */ + pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return 0; + + guard(mutex)(&arena->lock); + + if (uaddr) + ret = mtree_insert_range(&arena->mt, pgoff, pgoff + page_cnt - 1, + MT_ENTRY, GFP_KERNEL); + else + ret = mtree_alloc_range(&arena->mt, &pgoff, MT_ENTRY, + page_cnt, 0, page_cnt_max - 1, GFP_KERNEL); + if (ret) + goto out_free_pages; + + ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO, + node_id, page_cnt, pages); + if (ret) + goto out; + + uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); + /* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */ + ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, + kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); + if (ret) { + for (i = 0; i < page_cnt; i++) + __free_page(pages[i]); + goto out; + } + kvfree(pages); + return clear_lo32(arena->user_vm_start) + uaddr32; +out: + mtree_erase(&arena->mt, pgoff); +out_free_pages: + kvfree(pages); + return 0; +} + +/* + * If page is present in vmalloc area, unmap it from vmalloc area, + * unmap it from all user space vma-s, + * and free it. + */ +static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + struct vma_list *vml; + + list_for_each_entry(vml, &arena->vma_list, head) + zap_page_range_single(vml->vma, uaddr, + PAGE_SIZE * page_cnt, NULL); +} + +static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + u64 full_uaddr, uaddr_end; + long kaddr, pgoff, i; + struct page *page; + + /* only aligned lower 32-bit are relevant */ + uaddr = (u32)uaddr; + uaddr &= PAGE_MASK; + full_uaddr = clear_lo32(arena->user_vm_start) + uaddr; + uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT)); + if (full_uaddr >= uaddr_end) + return; + + page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT; + + guard(mutex)(&arena->lock); + + pgoff = compute_pgoff(arena, uaddr); + /* clear range */ + mtree_store_range(&arena->mt, pgoff, pgoff + page_cnt - 1, NULL, GFP_KERNEL); + + if (page_cnt > 1) + /* bulk zap if multiple pages being freed */ + zap_pages(arena, full_uaddr, page_cnt); + + kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr; + for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) { + page = vmalloc_to_page((void *)kaddr); + if (!page) + continue; + if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ + zap_pages(arena, full_uaddr, 1); + vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); + __free_page(page); + } +} + +__bpf_kfunc_start_defs(); + +__bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt, + int node_id, u64 flags) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt) + return NULL; + + return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id); +} + +__bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign) + return; + arena_free_pages(arena, (long)ptr__ign, page_cnt); +} +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(arena_kfuncs) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_KFUNCS_END(arena_kfuncs) + +static const struct btf_kfunc_id_set common_kfunc_set = { + .owner = THIS_MODULE, + .set = &arena_kfuncs, +}; + +static int __init kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); +} +late_initcall(kfunc_init); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 134b7979f537..a8ecf69c7754 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2976,6 +2976,17 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, { } +/* for configs without MMU or 32-bit */ +__weak const struct bpf_map_ops arena_map_ops; +__weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return 0; +} +__weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return 0; +} + #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f63f4da4db5e..67923e41a07e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -164,6 +164,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || @@ -479,6 +480,39 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + unsigned long nr_pages, struct page **pages) +{ + unsigned long i, j; + struct page *pg; + int ret = 0; +#ifdef CONFIG_MEMCG_KMEM + struct mem_cgroup *memcg, *old_memcg; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); +#endif + for (i = 0; i < nr_pages; i++) { + pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); + + if (pg) { + pages[i] = pg; + continue; + } + for (j = 0; j < i; j++) + __free_page(pages[j]); + ret = -ENOMEM; + break; + } + +#ifdef CONFIG_MEMCG_KMEM + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +#endif + return ret; +} + + static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; @@ -1176,6 +1210,7 @@ static int map_create(union bpf_attr *attr) } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; @@ -1265,6 +1300,7 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_ARENA: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bf084c693507..fbcf2e5e635a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18108,6 +18108,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_ARENA: break; default: verbose(env, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 85ec7fc799d7..e30d943db8a4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1009,6 +1009,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, __MAX_BPF_MAP_TYPE }; @@ -1396,6 +1397,12 @@ enum { /* BPF token FD is passed in a corresponding command's token_fd field */ BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), }; /* Flags for BPF_PROG_QUERY. */ @@ -1467,6 +1474,9 @@ union bpf_attr { * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the * number of hash functions (if 0, the bloom filter will default * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. */ __u64 map_extra; -- cgit v1.2.3 From 2fe99eb0ccf2bb73df65ebcbbf2f2ff70e63547b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:01 -0800 Subject: bpf: Add x86-64 JIT support for PROBE_MEM32 pseudo instructions. Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW] instructions. They are similar to PROBE_MEM instructions with the following differences: - PROBE_MEM has to check that the address is in the kernel range with src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE check - PROBE_MEM doesn't support store - PROBE_MEM32 relies on the verifier to clear upper 32-bit in the register - PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in %r12 in the prologue) Due to bpf_arena constructions such %r12 + %reg + off16 access is guaranteed to be within arena virtual range, so no address check at run-time. - PROBE_MEM32 allows STX and ST. If they fault the store is a nop. When LDX faults the destination register is zeroed. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/bpf/20240308010812.89848-4-alexei.starovoitov@gmail.com --- arch/x86/net/bpf_jit_comp.c | 191 +++++++++++++++++++++++++++++++++++++++++++- include/linux/bpf.h | 1 + include/linux/filter.h | 3 + 3 files changed, 194 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e1390d1e331b..38705a1abe62 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -113,6 +113,7 @@ static int bpf_size_to_x86_bytes(int bpf_size) /* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) #define X86_REG_R9 (MAX_BPF_JIT_REG + 2) +#define X86_REG_R12 (MAX_BPF_JIT_REG + 3) /* * The following table maps BPF registers to x86-64 registers. @@ -139,6 +140,7 @@ static const int reg2hex[] = { [BPF_REG_AX] = 2, /* R10 temp register */ [AUX_REG] = 3, /* R11 temp register */ [X86_REG_R9] = 1, /* R9 register, 6th function argument */ + [X86_REG_R12] = 4, /* R12 callee saved */ }; static const int reg2pt_regs[] = { @@ -167,6 +169,7 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_8) | BIT(BPF_REG_9) | BIT(X86_REG_R9) | + BIT(X86_REG_R12) | BIT(BPF_REG_AX)); } @@ -205,6 +208,17 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2) return byte; } +static u8 add_3mod(u8 byte, u32 r1, u32 r2, u32 index) +{ + if (is_ereg(r1)) + byte |= 1; + if (is_ereg(index)) + byte |= 2; + if (is_ereg(r2)) + byte |= 4; + return byte; +} + /* Encode 'dst_reg' register into x86-64 opcode 'byte' */ static u8 add_1reg(u8 byte, u32 dst_reg) { @@ -645,6 +659,8 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) + pop_r12(&prog); } EMIT1(0x58); /* pop rax */ @@ -704,6 +720,8 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) + pop_r12(&prog); } EMIT1(0x58); /* pop rax */ @@ -887,6 +905,18 @@ static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) *pprog = prog; } +static void emit_insn_suffix_SIB(u8 **pprog, u32 ptr_reg, u32 val_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + if (is_imm8(off)) { + EMIT3(add_2reg(0x44, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); + } else { + EMIT2_off32(add_2reg(0x84, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); + } + *pprog = prog; +} + /* * Emit a REX byte if it will be necessary to address these registers */ @@ -968,6 +998,37 @@ static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +static void emit_ldx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* movzx rax, byte ptr [rax + r12 + off] */ + EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB6); + break; + case BPF_H: + /* movzx rax, word ptr [rax + r12 + off] */ + EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB7); + break; + case BPF_W: + /* mov eax, dword ptr [rax + r12 + off] */ + EMIT2(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x8B); + break; + case BPF_DW: + /* mov rax, qword ptr [rax + r12 + off] */ + EMIT2(add_3mod(0x48, src_reg, dst_reg, index_reg), 0x8B); + break; + } + emit_insn_suffix_SIB(&prog, src_reg, dst_reg, index_reg, off); + *pprog = prog; +} + +static void emit_ldx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + emit_ldx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); +} + /* STX: *(u8*)(dst_reg + off) = src_reg */ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -1002,6 +1063,71 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +/* STX: *(u8*)(dst_reg + index_reg + off) = src_reg */ +static void emit_stx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* mov byte ptr [rax + r12 + off], al */ + EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x88); + break; + case BPF_H: + /* mov word ptr [rax + r12 + off], ax */ + EMIT3(0x66, add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); + break; + case BPF_W: + /* mov dword ptr [rax + r12 + 1], eax */ + EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); + break; + case BPF_DW: + /* mov qword ptr [rax + r12 + 1], rax */ + EMIT2(add_3mod(0x48, dst_reg, src_reg, index_reg), 0x89); + break; + } + emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off); + *pprog = prog; +} + +static void emit_stx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + emit_stx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); +} + +/* ST: *(u8*)(dst_reg + index_reg + off) = imm32 */ +static void emit_st_index(u8 **pprog, u32 size, u32 dst_reg, u32 index_reg, int off, int imm) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* mov byte ptr [rax + r12 + off], imm8 */ + EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC6); + break; + case BPF_H: + /* mov word ptr [rax + r12 + off], imm16 */ + EMIT3(0x66, add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); + break; + case BPF_W: + /* mov dword ptr [rax + r12 + 1], imm32 */ + EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); + break; + case BPF_DW: + /* mov qword ptr [rax + r12 + 1], imm32 */ + EMIT2(add_3mod(0x48, dst_reg, 0, index_reg), 0xC7); + break; + } + emit_insn_suffix_SIB(&prog, dst_reg, 0, index_reg, off); + EMIT(imm, bpf_size_to_x86_bytes(size)); + *pprog = prog; +} + +static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm) +{ + emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm); +} + static int emit_atomic(u8 **pprog, u8 atomic_op, u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { @@ -1043,12 +1169,15 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, return 0; } +#define DONT_CLEAR 1 + bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) { u32 reg = x->fixup >> 8; /* jump over faulting load and clear dest register */ - *(unsigned long *)((void *)regs + reg) = 0; + if (reg != DONT_CLEAR) + *(unsigned long *)((void *)regs + reg) = 0; regs->ip += x->fixup & 0xff; return true; } @@ -1147,11 +1276,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image bool tail_call_seen = false; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + u64 arena_vm_start; int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; int err; + arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena); + detect_reg_usage(insn, insn_cnt, callee_regs_used, &tail_call_seen); @@ -1172,8 +1304,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image push_r12(&prog); push_callee_regs(&prog, all_callee_regs_used); } else { + if (arena_vm_start) + push_r12(&prog); push_callee_regs(&prog, callee_regs_used); } + if (arena_vm_start) + emit_mov_imm64(&prog, X86_REG_R12, + arena_vm_start >> 32, (u32) arena_vm_start); ilen = prog - temp; if (rw_image) @@ -1564,6 +1701,56 @@ st: if (is_imm8(insn->off)) emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); break; + case BPF_ST | BPF_PROBE_MEM32 | BPF_B: + case BPF_ST | BPF_PROBE_MEM32 | BPF_H: + case BPF_ST | BPF_PROBE_MEM32 | BPF_W: + case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: + start_of_ldx = prog; + emit_st_r12(&prog, BPF_SIZE(insn->code), dst_reg, insn->off, insn->imm); + goto populate_extable; + + /* LDX: dst_reg = *(u8*)(src_reg + r12 + off) */ + case BPF_LDX | BPF_PROBE_MEM32 | BPF_B: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_H: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: + case BPF_STX | BPF_PROBE_MEM32 | BPF_B: + case BPF_STX | BPF_PROBE_MEM32 | BPF_H: + case BPF_STX | BPF_PROBE_MEM32 | BPF_W: + case BPF_STX | BPF_PROBE_MEM32 | BPF_DW: + start_of_ldx = prog; + if (BPF_CLASS(insn->code) == BPF_LDX) + emit_ldx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); + else + emit_stx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); +populate_extable: + { + struct exception_table_entry *ex; + u8 *_insn = image + proglen + (start_of_ldx - temp); + s64 delta; + + if (!bpf_prog->aux->extable) + break; + + if (excnt >= bpf_prog->aux->num_exentries) { + pr_err("mem32 extable bug\n"); + return -EFAULT; + } + ex = &bpf_prog->aux->extable[excnt++]; + + delta = _insn - (u8 *)&ex->insn; + /* switch ex to rw buffer for writes */ + ex = (void *)rw_image + ((void *)ex - (void *)image); + + ex->insn = delta; + + ex->data = EX_TYPE_BPF; + + ex->fixup = (prog - start_of_ldx) | + ((BPF_CLASS(insn->code) == BPF_LDX ? reg2pt_regs[dst_reg] : DONT_CLEAR) << 8); + } + break; + /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_PROBE_MEM | BPF_B: @@ -2036,6 +2223,8 @@ emit_jmp: pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (arena_vm_start) + pop_r12(&prog); } EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ea6ab6e0eef9..8904d1606125 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1458,6 +1458,7 @@ struct bpf_prog_aux { bool xdp_has_frags; bool exception_cb; bool exception_boundary; + struct bpf_arena *arena; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 36cc29a2934c..b119f04ecb0b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -72,6 +72,9 @@ struct ctl_table_header; /* unused opcode to mark special ldsx instruction. Same as BPF_IND */ #define BPF_PROBE_MEMSX 0x40 +/* unused opcode to mark special load instruction. Same as BPF_MSH */ +#define BPF_PROBE_MEM32 0xa0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 -- cgit v1.2.3 From 142fd4d2dcf58b1720a6af644f31de1a5551f219 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:02 -0800 Subject: bpf: Add x86-64 JIT support for bpf_addr_space_cast instruction. LLVM generates bpf_addr_space_cast instruction while translating pointers between native (zero) address space and __attribute__((address_space(N))). The addr_space=1 is reserved as bpf_arena address space. rY = addr_space_cast(rX, 0, 1) is processed by the verifier and converted to normal 32-bit move: wX = wY rY = addr_space_cast(rX, 1, 0) has to be converted by JIT: aux_reg = upper_32_bits of arena->user_vm_start aux_reg <<= 32 wX = wY // clear upper 32 bits of dst register if (wX) // if not zero add upper bits of user_vm_start wX |= aux_reg JIT can do it more efficiently: mov dst_reg32, src_reg32 // 32-bit move shl dst_reg, 32 or dst_reg, user_vm_start rol dst_reg, 32 xor r11, r11 test dst_reg32, dst_reg32 // check if lower 32-bit are zero cmove r11, dst_reg // if so, set dst_reg to zero // Intel swapped src/dst register encoding in CMOVcc Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20240308010812.89848-5-alexei.starovoitov@gmail.com --- arch/x86/net/bpf_jit_comp.c | 42 +++++++++++++++++++++++++++++++++++++++++- include/linux/filter.h | 1 + kernel/bpf/core.c | 5 +++++ 3 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 38705a1abe62..27058d7395f6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1276,13 +1276,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image bool tail_call_seen = false; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - u64 arena_vm_start; + u64 arena_vm_start, user_vm_start; int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; int err; arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena); + user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena); detect_reg_usage(insn, insn_cnt, callee_regs_used, &tail_call_seen); @@ -1350,6 +1351,40 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image break; case BPF_ALU64 | BPF_MOV | BPF_X: + if (insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16) { + if (dst_reg != src_reg) + /* 32-bit mov */ + emit_mov_reg(&prog, false, dst_reg, src_reg); + /* shl dst_reg, 32 */ + maybe_emit_1mod(&prog, dst_reg, true); + EMIT3(0xC1, add_1reg(0xE0, dst_reg), 32); + + /* or dst_reg, user_vm_start */ + maybe_emit_1mod(&prog, dst_reg, true); + if (is_axreg(dst_reg)) + EMIT1_off32(0x0D, user_vm_start >> 32); + else + EMIT2_off32(0x81, add_1reg(0xC8, dst_reg), user_vm_start >> 32); + + /* rol dst_reg, 32 */ + maybe_emit_1mod(&prog, dst_reg, true); + EMIT3(0xC1, add_1reg(0xC0, dst_reg), 32); + + /* xor r11, r11 */ + EMIT3(0x4D, 0x31, 0xDB); + + /* test dst_reg32, dst_reg32; check if lower 32-bit are zero */ + maybe_emit_mod(&prog, dst_reg, dst_reg, false); + EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); + + /* cmove r11, dst_reg; if so, set dst_reg to zero */ + /* WARNING: Intel swapped src/dst register encoding in CMOVcc !!! */ + maybe_emit_mod(&prog, AUX_REG, dst_reg, true); + EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg)); + break; + } + fallthrough; case BPF_ALU | BPF_MOV | BPF_X: if (insn->off == 0) emit_mov_reg(&prog, @@ -3432,6 +3467,11 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, } } +bool bpf_jit_supports_arena(void) +{ + return true; +} + bool bpf_jit_supports_ptr_xchg(void) { return true; diff --git a/include/linux/filter.h b/include/linux/filter.h index b119f04ecb0b..c99bc3df2d28 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -962,6 +962,7 @@ bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); +bool bpf_jit_supports_arena(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a8ecf69c7754..bdbdc75cdcd5 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2932,6 +2932,11 @@ bool __weak bpf_jit_supports_far_kfunc_call(void) return false; } +bool __weak bpf_jit_supports_arena(void) +{ + return false; +} + /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same -- cgit v1.2.3 From 6082b6c328b5486da2b356eae94b8b83c98b5565 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:03 -0800 Subject: bpf: Recognize addr_space_cast instruction in the verifier. rY = addr_space_cast(rX, 0, 1) tells the verifier that rY->type = PTR_TO_ARENA. Any further operations on PTR_TO_ARENA register have to be in 32-bit domain. The verifier will mark load/store through PTR_TO_ARENA with PROBE_MEM32. JIT will generate them as kern_vm_start + 32bit_addr memory accesses. rY = addr_space_cast(rX, 1, 0) tells the verifier that rY->type = unknown scalar. If arena->map_flags has BPF_F_NO_USER_CONV set then convert cast_user to mov32 as well. Otherwise JIT will convert it to: rY = (u32)rX; if (rY) rY |= arena->user_vm_start & ~(u64)~0U; Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240308010812.89848-6-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + kernel/bpf/log.c | 3 ++ kernel/bpf/syscall.c | 6 +++ kernel/bpf/verifier.c | 107 +++++++++++++++++++++++++++++++++++++++---- 5 files changed, 109 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8904d1606125..d0c836ba009d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -883,6 +883,7 @@ enum bpf_reg_type { * an explicit null check is required for this struct. */ PTR_TO_MEM, /* reg points to valid memory region */ + PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 4b0f6600e499..7cb1b75eee38 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -548,6 +548,7 @@ struct bpf_insn_aux_data { u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ + bool needs_zext; /* alu op needs to clear upper bits */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ bool is_iter_next; /* bpf_iter__next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 63c34e7b0715..2a243cf37c60 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -458,6 +458,7 @@ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", + [PTR_TO_ARENA] = "arena", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", @@ -693,6 +694,8 @@ static void print_reg_state(struct bpf_verifier_env *env, } verbose(env, "%s", reg_type_str(env, t)); + if (t == PTR_TO_ARENA) + return; if (t == PTR_TO_STACK) { if (state->frameno != reg->frameno) verbose(env, "[%d]", reg->frameno); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 67923e41a07e..07f2a4db4511 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4453,6 +4453,12 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, continue; } + if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || + BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { + insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; + continue; + } + if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fbcf2e5e635a..1358e20d315a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4386,6 +4386,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: + case PTR_TO_ARENA: return true; default: return false; @@ -5828,6 +5829,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; + case PTR_TO_ARENA: + return 0; default: break; } @@ -6937,6 +6940,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_ARENA) { + if (t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); @@ -8408,6 +8414,7 @@ static int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: + case PTR_TO_ARENA: case SCALAR_VALUE: return 0; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows @@ -13852,6 +13859,21 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; src_reg = NULL; + + if (dst_reg->type == PTR_TO_ARENA) { + struct bpf_insn_aux_data *aux = cur_aux(env); + + if (BPF_CLASS(insn->code) == BPF_ALU64) + /* + * 32-bit operations zero upper bits automatically. + * 64-bit operations need to be converted to 32. + */ + aux->needs_zext = true; + + /* Any arithmetic operations are allowed on arena pointers */ + return 0; + } + if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; else @@ -13969,19 +13991,20 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { - if (insn->imm != 0) { - verbose(env, "BPF_MOV uses reserved fields\n"); - return -EINVAL; - } - if (BPF_CLASS(insn->code) == BPF_ALU) { - if (insn->off != 0 && insn->off != 8 && insn->off != 16) { + if ((insn->off != 0 && insn->off != 8 && insn->off != 16) || + insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } + } else if (insn->off == BPF_ADDR_SPACE_CAST) { + if (insn->imm != 1 && insn->imm != 1u << 16) { + verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); + return -EINVAL; + } } else { - if (insn->off != 0 && insn->off != 8 && insn->off != 16 && - insn->off != 32) { + if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && + insn->off != 32) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } @@ -14008,7 +14031,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { - if (insn->off == 0) { + if (insn->imm) { + /* off == BPF_ADDR_SPACE_CAST */ + mark_reg_unknown(env, regs, insn->dst_reg); + if (insn->imm == 1) /* cast from as(1) to as(0) */ + dst_reg->type = PTR_TO_ARENA; + } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg */ @@ -15182,6 +15210,10 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { + if (map->map_type == BPF_MAP_TYPE_ARENA) { + __mark_reg_unknown(env, dst_reg); + return 0; + } dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; WARN_ON_ONCE(map->max_entries != 1); @@ -16568,6 +16600,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * the same stack frame, since fp-8 in foo != fp-8 in bar */ return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; + case PTR_TO_ARENA: + return true; default: return regs_exact(rold, rcur, idmap); } @@ -17443,6 +17477,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: + case PTR_TO_ARENA: return false; default: return true; @@ -18296,6 +18331,31 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) fdput(f); return -EBUSY; } + if (map->map_type == BPF_MAP_TYPE_ARENA) { + if (env->prog->aux->arena) { + verbose(env, "Only one arena per program\n"); + fdput(f); + return -EBUSY; + } + if (!env->allow_ptr_leaks || !env->bpf_capable) { + verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); + fdput(f); + return -EPERM; + } + if (!env->prog->jit_requested) { + verbose(env, "JIT is required to use arena\n"); + return -EOPNOTSUPP; + } + if (!bpf_jit_supports_arena()) { + verbose(env, "JIT doesn't support arena\n"); + return -EOPNOTSUPP; + } + env->prog->aux->arena = (void *)map; + if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { + verbose(env, "arena's user address must be set via map_extra or mmap()\n"); + return -EINVAL; + } + } fdput(f); next_insn: @@ -18917,6 +18977,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) env->prog->aux->num_exentries++; } continue; + case PTR_TO_ARENA: + if (BPF_MODE(insn->code) == BPF_MEMSX) { + verbose(env, "sign extending loads from arena are not supported yet\n"); + return -EOPNOTSUPP; + } + insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code); + env->prog->aux->num_exentries++; + continue; default: continue; } @@ -19102,13 +19170,19 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; + func[i]->aux->arena = prog->aux->arena; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEM32 || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) num_exentries++; + if ((BPF_CLASS(insn->code) == BPF_STX || + BPF_CLASS(insn->code) == BPF_ST) && + BPF_MODE(insn->code) == BPF_PROBE_MEM32) + num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; @@ -19507,6 +19581,21 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } for (i = 0; i < insn_cnt;) { + if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) { + if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) || + (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { + /* convert to 32-bit mov that clears upper 32-bit */ + insn->code = BPF_ALU | BPF_MOV | BPF_X; + /* clear off, so it's a normal 'wX = wY' from JIT pov */ + insn->off = 0; + } /* cast from as(0) to as(1) should be handled by JIT */ + goto next_insn; + } + + if (env->insn_aux_data[i + delta].needs_zext) + /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */ + insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code); + /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || -- cgit v1.2.3 From 2edc3de6fb650924a87fffebebc3b7572cbf6e38 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:04 -0800 Subject: bpf: Recognize btf_decl_tag("arg: Arena") as PTR_TO_ARENA. In global bpf functions recognize btf_decl_tag("arg:arena") as PTR_TO_ARENA. Note, when the verifier sees: __weak void foo(struct bar *p) it recognizes 'p' as PTR_TO_MEM and 'struct bar' has to be a struct with scalars. Hence the only way to use arena pointers in global functions is to tag them with "arg:arena". Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/bpf/20240308010812.89848-7-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + kernel/bpf/btf.c | 19 +++++++++++++++---- kernel/bpf/verifier.c | 15 +++++++++++++++ 3 files changed, 31 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0c836ba009d..08ad265cb195 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -712,6 +712,7 @@ enum bpf_arg_type { * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ + ARG_PTR_TO_ARENA, ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 170d017e8e4a..90c4a32d89ff 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7111,10 +7111,11 @@ cand_cache_unlock: } enum btf_arg_tag { - ARG_TAG_CTX = 0x1, - ARG_TAG_NONNULL = 0x2, - ARG_TAG_TRUSTED = 0x4, - ARG_TAG_NULLABLE = 0x8, + ARG_TAG_CTX = BIT_ULL(0), + ARG_TAG_NONNULL = BIT_ULL(1), + ARG_TAG_TRUSTED = BIT_ULL(2), + ARG_TAG_NULLABLE = BIT_ULL(3), + ARG_TAG_ARENA = BIT_ULL(4), }; /* Process BTF of a function to produce high-level expectation of function @@ -7226,6 +7227,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) tags |= ARG_TAG_NONNULL; } else if (strcmp(tag, "nullable") == 0) { tags |= ARG_TAG_NULLABLE; + } else if (strcmp(tag, "arena") == 0) { + tags |= ARG_TAG_ARENA; } else { bpf_log(log, "arg#%d has unsupported set of tags\n", i); return -EOPNOTSUPP; @@ -7280,6 +7283,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) sub->args[i].btf_id = kern_type_id; continue; } + if (tags & ARG_TAG_ARENA) { + if (tags & ~ARG_TAG_ARENA) { + bpf_log(log, "arg#%d arena cannot be combined with any other tags\n", i); + return -EINVAL; + } + sub->args[i].arg_type = ARG_PTR_TO_ARENA; + continue; + } if (is_global) { /* generic user data pointer */ u32 mem_size; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1358e20d315a..d64f7a9b60e8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9379,6 +9379,18 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, bpf_log(log, "arg#%d is expected to be non-NULL\n", i); return -EINVAL; } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* + * Can pass any value and the kernel won't crash, but + * only PTR_TO_ARENA or SCALAR make sense. Everything + * else is a bug in the bpf program. Point it out to + * the user at the verification time instead of + * run-time debug nightmare. + */ + if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a pointer to arena or scalar.\n", regno); + return -EINVAL; + } } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) @@ -20448,6 +20460,9 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ reg->btf_id = arg->btf_id; reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* caller can pass either PTR_TO_ARENA or SCALAR */ + mark_reg_unknown(env, regs, i); } else { WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", i - BPF_REG_1, arg->arg_type); -- cgit v1.2.3 From 66c8473135c62f478301a0e5b3012f203562dfa6 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 8 Mar 2024 16:47:39 -0800 Subject: bpf: move sleepable flag from bpf_prog_aux to bpf_prog prog->aux->sleepable is checked very frequently as part of (some) BPF program run hot paths. So this extra aux indirection seems wasteful and on busy systems might cause unnecessary memory cache misses. Let's move sleepable flag into prog itself to eliminate unnecessary pointer dereference. Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Message-ID: <20240309004739.2961431-1-andrii@kernel.org> Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++---- kernel/bpf/bpf_iter.c | 4 ++-- kernel/bpf/core.c | 2 +- kernel/bpf/syscall.c | 6 +++--- kernel/bpf/trampoline.c | 4 ++-- kernel/bpf/verifier.c | 12 ++++++------ kernel/events/core.c | 2 +- kernel/trace/bpf_trace.c | 2 +- net/bpf/bpf_dummy_struct_ops.c | 2 +- 9 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 08ad265cb195..4f20f62f9d63 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1455,7 +1455,6 @@ struct bpf_prog_aux { bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; - bool sleepable; bool tail_call_reachable; bool xdp_has_frags; bool exception_cb; @@ -1541,7 +1540,8 @@ struct bpf_prog { enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ - tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ + tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */ + sleepable:1; /* BPF program is sleepable */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -2112,14 +2112,14 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { - if (!prog->aux->sleepable) + if (!prog->sleepable) rcu_read_lock(); run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; - if (!prog->aux->sleepable) + if (!prog->sleepable) rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 0fae79164187..112581cf97e7 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -548,7 +548,7 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, return -ENOENT; /* Only allow sleepable program for resched-able iterator */ - if (prog->aux->sleepable && !bpf_iter_target_support_resched(tinfo)) + if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) return -EINVAL; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); @@ -697,7 +697,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; - if (prog->aux->sleepable) { + if (prog->sleepable) { rcu_read_lock_trace(); migrate_disable(); might_fault(); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 297184baeb2d..696bc55de8e8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2706,7 +2706,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, bool sleepable; u32 i; - sleepable = aux->sleepable; + sleepable = aux->prog->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 07f2a4db4511..ae2ff73bde7e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2248,7 +2248,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) btf_put(prog->aux->attach_btf); if (deferred) { - if (prog->aux->sleepable) + if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); @@ -2813,11 +2813,11 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) } prog->expected_attach_type = attr->expected_attach_type; + prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; - prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; /* move token into prog->aux, reuse taken refcnt */ @@ -5554,7 +5554,7 @@ static int bpf_prog_bind_map(union bpf_attr *attr) /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ - if (prog->aux->sleepable) + if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index d382f5ebe06c..db7599c59c78 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1014,7 +1014,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_enter_sleepable_recur : @@ -1029,7 +1029,7 @@ bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_exit_sleepable_recur : diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d64f7a9b60e8..d501c90f8ab5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5274,7 +5274,7 @@ bad_type: static bool in_sleepable(struct bpf_verifier_env *env) { - return env->prog->aux->sleepable; + return env->prog->sleepable; } /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() @@ -18137,7 +18137,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } - if (prog->aux->sleepable) + if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: @@ -18325,7 +18325,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) return -E2BIG; } - if (env->prog->aux->sleepable) + if (env->prog->sleepable) atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it @@ -20938,7 +20938,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, } } - if (prog->aux->sleepable) { + if (prog->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: @@ -21049,14 +21049,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { - if (prog->aux->sleepable) + if (prog->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } - if (prog->aux->sleepable && !can_be_sleepable(prog)) { + if (prog->sleepable && !can_be_sleepable(prog)) { verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 5ecfa57e3b97..724e6d7e128f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10553,7 +10553,7 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, (is_syscall_tp && prog->type != BPF_PROG_TYPE_TRACEPOINT)) return -EINVAL; - if (prog->type == BPF_PROG_TYPE_KPROBE && prog->aux->sleepable && !is_uprobe) + if (prog->type == BPF_PROG_TYPE_KPROBE && prog->sleepable && !is_uprobe) /* only uprobe programs are allowed to be sleepable */ return -EINVAL; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 241ddf5e3895..0a5c4efc73c3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3256,7 +3256,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, .uprobe = uprobe, }; struct bpf_prog *prog = link->link.prog; - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; struct bpf_run_ctx *old_run_ctx; int err = 0; diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 1b5f812e6972..de33dc1b0daa 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -174,7 +174,7 @@ static int bpf_dummy_ops_check_member(const struct btf_type *t, case offsetof(struct bpf_dummy_ops, test_sleepable): break; default: - if (prog->aux->sleepable) + if (prog->sleepable) return -EINVAL; } -- cgit v1.2.3